© 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. 49109
    Prev
    Next
    INDEX
    Explanations

    /wp

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

    modeltrained with context length

    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
     uang
    0.48
    ℍ
    0.45
    лова
    0.45
     देतात
    0.43
    ເຮ
    0.43
    ريف
    0.43
    賁
    0.42
     व्यापारी
    0.42
     Compañ
    0.42
    凌
    0.42
    POSITIVE LOGITS
    in
    0.67
    as
    0.65
    a
    0.65
    et
    0.56
    ya
    0.55
    e
    0.54
    inprogress
    0.52
    b
    0.52
    es
    0.52
     in
    0.52
    Activations Density 0.000%

    No Known Activations