© 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. 5896
    Prev
    Next
    INDEX
    Explanations

    years in parentheses

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

    numbers and code elements

    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
    ০০০
    0.26
    ২৯
    0.23
    ০০
    0.23
    _
    0.23
    ००
    0.22
    HAO
    0.22
    dpi
    0.21
     miljoen
    0.21
    staaten
    0.21
    directory
    0.21
    POSITIVE LOGITS
     ロー
    0.19
     فعل
    0.19
     বৈ
    0.18
    شوف
    0.18
     سان
    0.18
     Clifford
    0.18
     Lambert
    0.18
     pat
    0.18
     为了
    0.18
    з
    0.18
    Activations Density 0.474%

    No Known Activations