© 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. 34696
    Prev
    Next
    INDEX
    Explanations

    providing information or services

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

    geographical and technical terms

    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
     L
    0.46
     W
    0.46
     Novem
    0.42
    Particip
    0.42
     G
    0.41
    يب
    0.41
     ب
    0.41
    Ｖ
    0.41
     R
    0.41
     لد
    0.41
    POSITIVE LOGITS
    CaCl
    0.47
     एवरीवन
    0.46
    ག་
    0.44
    arach
    0.43
    ང
    0.43
     दर
    0.43
    schule
    0.43
    enough
    0.42
    पेपर
    0.42
    damian
    0.42
    Activations Density 0.000%

    No Known Activations