© 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. 61230
    Prev
    Next
    INDEX
    Explanations

    amazing art, game, offers

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

    vs

    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
     reimb
    0.49
     cell
    0.47
     कोशिका
    0.46
    剛剛
    0.46
     রূপ
    0.45
    忝
    0.44
     समाधान
    0.44
     Erk
    0.43
    謢
    0.43
     reimburse
    0.43
    POSITIVE LOGITS
    equations
    0.47
    commun
    0.46
    Type
    0.44
    oflu
    0.44
     ブ
    0.43
    rological
    0.42
    hrlich
    0.42
    たくさん
    0.42
    achron
    0.42
     peculiarities
    0.42
    Activations Density 0.000%

    No Known Activations