© 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. 35569
    Prev
    Next
    INDEX
    Explanations

    customary tagline

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

    listing specifications

    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
    er
    0.49
    d
    0.48
    ives
    0.46
    es
    0.46
    u
    0.46
    라
    0.45
     is
    0.44
     ace
    0.42
     Paulo
    0.42
    in
    0.42
    POSITIVE LOGITS
    ឬ
    0.46
     ឬ
    0.45
    vVertex
    0.44
    $)$.
    0.43
     عادة
    0.43
    relativePath
    0.43
     عادت
    0.42
    بع
    0.42
    řit
    0.42
     حضور
    0.42
    Activations Density 0.000%

    No Known Activations