© 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. 42696
    Prev
    Next
    INDEX
    Explanations

    contracts, markets, love

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

    purpose or to provide

    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
    ́s
    0.43
    iman
    0.43
    mêmes
    0.43
    izoph
    0.43
     kapital
    0.42
    ኖ
    0.42
    പര
    0.42
     perform
    0.41
    ٥
    0.41
     murdering
    0.41
    POSITIVE LOGITS
    育て
    0.46
    合同
    0.45
    CONTRACT
    0.44
     volatil
    0.43
    季节
    0.43
     jaunâtre
    0.43
     periód
    0.43
     خشک
    0.41
     skú
    0.40
     contratos
    0.40
    Activations Density 0.000%

    No Known Activations