© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 9659
    Prev
    Next
    INDEX
    Explanations

    your hand

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

    lean protein

    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
    s
    0.46
    Older
    0.44
    響
    0.44
    Introduction
    0.43
    e
    0.43
    l
    0.43
    ING
    0.42
    Simple
    0.42
    Т
    0.42
     drums
    0.42
    POSITIVE LOGITS
     sorgen
    0.52
     shareholder
    0.50
     Zagreb
    0.50
     बेंगल
    0.47
     fxaa
    0.47
    defn
    0.47
     ဆ
    0.47
     benz
    0.46
     machte
    0.46
     potensi
    0.46
    Activations Density 0.000%

    No Known Activations