© 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. 190505
    Prev
    Next
    INDEX
    Explanations

    limiting user entitlements

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

    foreign language content

    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
    PRODUCTION
    0.52
    כ
    0.46
     subdue
    0.45
     femen
    0.44
     obsession
    0.44
    CHROM
    0.44
     inflate
    0.43
     suscrib
    0.43
    Rationale
    0.43
    խ
    0.43
    POSITIVE LOGITS
    elä
    0.50
     मई
    0.50
     ডিজি
    0.50
     keiner
    0.49
     bacon
    0.48
     dagen
    0.47
    ‌های
    0.46
    erei
    0.46
    áticos
    0.45
     Tron
    0.45
    Activations Density 0.000%

    No Known Activations