© 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. 50681
    Prev
    Next
    INDEX
    Explanations

    about statements

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

    power dynamics

    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
     কী
    0.52
    ㌔
    0.49
     panneaux
    0.49
    кновен
    0.48
     রাজেশ
    0.48
    テール
    0.48
     おい
    0.47
     thân
    0.47
     স্পষ্টভাবে
    0.47
     என்ன
    0.47
    POSITIVE LOGITS
     feel
    0.48
    unk
    0.45
    ↵
    0.44
    ere
    0.44
    url
    0.43
    Ме
    0.43
     dens
    0.43
    ]]></
    0.42
     feels
    0.41
     unbeatable
    0.41
    Activations Density 0.000%

    No Known Activations