© 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. 6642
    Prev
    Next
    INDEX
    Explanations

    induct / under / into / above / % / convey / many / closer / for

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

    This neuron strongly activates on the first meaningful word of a sentence (i.e. sentence-initial content 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_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
    ेयर
    0.70
     शिशु
    0.70
    ereal
    0.70
    eru
    0.70
     ریاست
    0.68
     مخصوص
    0.68
    鲲
    0.67
    ok
    0.66
    idos
    0.66
    edi
    0.66
    POSITIVE LOGITS
     tions
    0.84
     février
    0.82
    训
    0.82
     quantile
    0.80
     notre
    0.79
     svm
    0.78
     %>
    0.77
     philosoph
    0.77
     spel
    0.77
     prendre
    0.77
    Activations Density 0.000%

    No Known Activations