© 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. 13157
    Prev
    Next
    INDEX
    Explanations

    prefixes forming words

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

    The neuron flags the main content words (i.e. the distinctive, usually capitalized nouns or adjectives) in book and article titles.

    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
    cenik
    0.95
    enderung
    0.94
    <unused1879>
    0.91
     पॉलिटी
    0.89
    ilización
    0.87
    ksz
    0.86
    ángulos
    0.86
    <unused209>
    0.86
    𝚣
    0.85
    udahkan
    0.84
    POSITIVE LOGITS
     which
    0.84
     and
    0.83
     but
    0.82
     such
    0.81
    0.80
    -
    0.79
     below
    0.77
     after
    0.74
     people
    0.74
     or
    0.73
    Activations Density 0.016%

    No Known Activations