© 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. 12818
    Prev
    Next
    INDEX
    Explanations

    titles and names

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

    The neuron fires on distinctive proper names and titles (e.g. of songs, films, books, places, and events).

    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
    Week
    0.65
     Week
    0.63
    W
    0.63
    WEEK
    0.58
    ®
    0.57
     Essentials
    0.53
    वण्यासाठी
    0.53
    TOD
    0.52
    N
    0.52
    U
    0.51
    POSITIVE LOGITS
    上映
    0.56
     strangled
    0.49
     extrapolated
    0.48
     faintly
    0.48
     currant
    0.47
     uncoated
    0.47
    stringProp
    0.46
     tendo
    0.46
    <unused2130>
    0.46
     подру
    0.46
    Activations Density 0.220%

    No Known Activations