© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 152655
    Prev
    Next
    INDEX
    Explanations

    agency, juice, tree, olive

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

    discussing harmful words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
     sviluppo
    0.59
    スマートフォン
    0.50
     речи
    0.48
    miot
    0.48
    iszt
    0.47
     ..."
    0.47
    smartphone
    0.47
     駅
    0.46
    ata
    0.46
     அவரது
    0.46
    POSITIVE LOGITS
    :
    0.50
     રાશિફળ
    0.48
     Nutrient
    0.47
     EW
    0.46
    籬
    0.45
     Agh
    0.45
     pkt
    0.44
     Supp
    0.44
     Considerable
    0.44
    =
    0.44
    Activations Density 0.000%

    No Known Activations