© 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. 182703
    Prev
    Next
    INDEX
    Explanations

    institutional investors

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

    can give

    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
    瑯
    0.54
     ಕುಟ
    0.52
    द्योगिक
    0.47
    我們可以
    0.46
    🕸
    0.45
    goài
    0.45
     ಸಂಬ
    0.45
     পাবার
    0.45
    Ⲑ
    0.44
    grond
    0.44
    POSITIVE LOGITS
     unexpected
    0.50
     an
    0.50
     unforeseen
    0.48
     selezione
    0.46
     ‘
    0.46
     accommodate
    0.45
     unanticipated
    0.44
     get
    0.43
    出现
    0.43
     “
    0.43
    Activations Density 0.000%

    No Known Activations