© 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. 838
    Prev
    Next
    INDEX
    Explanations

    adverbial suffixes

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

    jokes about skeletons

    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
    冏
    0.41
    REGI
    0.39
     WTF
    0.37
    ందరు
    0.36
    瘧
    0.36
     CMV
    0.36
    ワク
    0.35
     COE
    0.35
    겅
    0.35
     BCH
    0.35
    POSITIVE LOGITS
     crossword
    0.41
     carelessly
    0.36
     display
    0.35
     amiss
    0.35
    endsWith
    0.34
    ප
    0.34
     Не
    0.33
     Features
    0.33
     lawn
    0.33
     例如
    0.33
    Activations Density 0.023%

    No Known Activations