© 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. 31-GEMMASCOPE-2-RES-16K
    7. 12908
    Prev
    Next
    INDEX
    Explanations

    describing details or opportunities

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

    This neuron activates on content-bearing words (longer, domain-specific nouns and verbs) while ignoring common function words.

    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_31_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
    -
    0.74
    ë
    0.69
     tuli
    0.59
    '
    0.59
     deed
    0.57
    сс
    0.57
    ness
    0.56
     work
    0.55
     sute
    0.55
     Ross
    0.53
    POSITIVE LOGITS
     নিতান্ত
    0.70
    Proveedor
    0.64
     पोषक
    0.64
     tzv
    0.62
    NaClO
    0.62
     単
    0.62
    唪
    0.62
    udarstvennyj
    0.61
    imar
    0.61
     חד
    0.61
    Activations Density 0.019%

    No Known Activations