© 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. 143937
    Prev
    Next
    INDEX
    Explanations

    Available in

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

    Waist-to-Hip Ratio

    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
     ഞാൻ
    0.48
     começando
    0.47
     करण्यासाठी
    0.46
    ಿಯಿಂದ
    0.46
    तीने
    0.46
     wanneer
    0.46
    䐍
    0.46
     tekan
    0.46
     tentando
    0.45
     opge
    0.45
    POSITIVE LOGITS
    _
    0.42
     disorders
    0.42
    Factory
    0.40
    COR
    0.40
    Differences
    0.40
     bedrock
    0.40
    FINAL
    0.40
     builders
    0.39
    Addresses
    0.39
    QUIN
    0.39
    Activations Density 0.001%

    No Known Activations