© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 1964
    Prev
    Next
    INDEX
    Explanations

    a few, a lot

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron detects first-person, self-referential statements by firing strongly on occurrences of “I.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    the article "a" when it appears before quantifying or measuring expressions.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    the indefinite article “a” when it introduces fixed quantity or degree expressions (a + quantifier/measure phrase).

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    jenigen
    0.76
     vultures
    0.70
     ponctuées
    0.66
     slums
    0.64
     bárm
    0.63
     empêcher
    0.63
     ponctué
    0.62
     weeds
    0.62
     oligodend
    0.61
    dır
    0.61
    POSITIVE LOGITS
    sex
    0.92
    string
    0.73
    omore
    0.72
     and
    0.72
     और
    0.71
     were
    0.70
     few
    0.69
     và
    0.68
     not
    0.68
    sext
    0.67
    Activations Density 0.005%

    No Known Activations