© 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. 164295
    Prev
    Next
    INDEX
    Explanations

    organizational or technical structure

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

    measurement ranges

    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
     HP
    0.44
    T
    0.44
    第一
    0.43
    查
    0.43
     I
    0.42
    جميع
    0.42
    HP
    0.42
     Giac
    0.41
    Vi
    0.41
    Hi
    0.40
    POSITIVE LOGITS
     ważne
    0.54
    ɩ
    0.50
    DeleteDialogOpen
    0.48
    눌
    0.47
    щност
    0.47
     खासकर
    0.46
    GTUIKit
    0.46
     răsp
    0.46
    ildiği
    0.46
    łego
    0.45
    Activations Density 0.001%

    No Known Activations