© 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. 154530
    Prev
    Next
    INDEX
    Explanations

    vpn tunnel, staging, moment, score, tanker

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

    predictable irrationality or financial gain

    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
     reorgan
    0.52
     पोहो
    0.50
     बारीक
    0.49
     علمی
    0.49
     छ
    0.48
     доклад
    0.48
     ín
    0.47
     چون
    0.47
     こんな
    0.47
    詳しい
    0.47
    POSITIVE LOGITS
    );
    0.47
    Slide
    0.47
    Investment
    0.46
    is
    0.46
    $
    0.45
    Function
    0.44
    DF
    0.44
    %
    0.44
    马
    0.44
    ীয়
    0.44
    Activations Density 0.001%

    No Known Activations