© 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. 217001
    Prev
    Next
    INDEX
    Explanations

    ship every

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

    apple

    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
    IDF
    0.47
     assaulting
    0.45
    Λ
    0.44
    Robert
    0.42
     extrait
    0.42
     способов
    0.42
     ম্যাজিস্ট
    0.42
     airborne
    0.41
     Barron
    0.41
     Feuilles
    0.41
    POSITIVE LOGITS
    ças
    0.54
    qa
    0.52
     ा
    0.50
    builders
    0.50
    ående
    0.49
    ål
    0.49
    rior
    0.47
    ible
    0.47
    ys
    0.47
     yahoo
    0.47
    Activations Density 0.000%

    No Known Activations