© 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. 32377
    Prev
    Next
    INDEX
    Explanations

    cards withmusical instrumentswhite ocean

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

    essential importance

    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
    ту
    0.49
    택
    0.47
    тельного
    0.46
    ст
    0.45
     mjes
    0.44
    фи
    0.44
    संयुक्त
    0.44
    льна
    0.43
    си
    0.42
    тно
    0.41
    POSITIVE LOGITS
     Enables
    0.52
    呓
    0.49
     शक्यता
    0.46
     Retrie
    0.46
     Remain
    0.46
     Removes
    0.46
     Episodes
    0.46
     fellows
    0.45
     zostały
    0.45
     annunci
    0.45
    Activations Density 0.000%

    No Known Activations