© 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. 143654
    Prev
    Next
    INDEX
    Explanations

    llvm function info

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

    code blocks

    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
    COMPILE
    0.39
     onError
    0.37
     *)
    0.37
    onError
    0.37
    \,.
    0.37
     باتوں
    0.37
     ANALYSIS
    0.36
     policymakers
    0.36
     三
    0.36
     先
    0.36
    POSITIVE LOGITS
    iber
    0.45
    anek
    0.42
    ren
    0.40
    rest
    0.40
    ruit
    0.40
    odem
    0.40
    Diam
    0.40
    bl
    0.40
    ripe
    0.39
    buah
    0.39
    Activations Density 0.000%

    No Known Activations