© 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. 70677
    Prev
    Next
    INDEX
    Explanations

    contact your customs office

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

    conditions or contributing factors

    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
     repair
    0.51
     हाथ
    0.48
    ä
    0.48
     role
    0.48
    flare
    0.47
    oidal
    0.46
    ethe
    0.46
    ethanol
    0.46
    credit
    0.45
     said
    0.45
    POSITIVE LOGITS
     fieldContext
    0.53
    莓
    0.47
     Wishes
    0.47
    ériences
    0.46
    পট
    0.46
     dél
    0.44
     popOperand
    0.44
     TInner
    0.43
    HALL
    0.43
    策划
    0.43
    Activations Density 0.000%

    No Known Activations