© 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. 134312
    Prev
    Next
    INDEX
    Explanations

    urls

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

    causes/forces/holds

    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
     AML
    0.48
     Comercio
    0.47
    ぷ
    0.46
    👛
    0.46
     美国
    0.46
    鞋
    0.46
    或者
    0.45
     Async
    0.45
     Comunicación
    0.45
     кнопку
    0.45
    POSITIVE LOGITS
    ᅮ
    0.47
    vasion
    0.46
    failure
    0.44
     recomp
    0.44
    uffling
    0.43
    igg
    0.43
     scanty
    0.43
    UNO
    0.42
    afety
    0.42
     satte
    0.41
    Activations Density 0.000%

    No Known Activations