© 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. 4863
    Prev
    Next
    INDEX
    Explanations

    titles of academic books

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

    The neuron responds to document section headings or titles—especially sequences of (mostly) uppercase words often ending with a colon.

    oai_token-act-pair · o4-miniTriggered 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
    :
    0.76
    ’:
    0.66
    ঃ
    0.63
    ’-
    0.61
    ”:
    0.61
    -
    0.61
    '-
    0.60
    ’”
    0.58
    ”“
    0.57
    ”;
    0.56
    POSITIVE LOGITS
     The
    1.12
     An
    1.11
     A
    1.09
    The
    1.04
    1
    1.00
    An
    0.95
    ﺎ
    0.92
     În
    0.89
     From
    0.88
     الأ
    0.87
    Activations Density 0.003%

    No Known Activations