© 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. 36203
    Prev
    Next
    INDEX
    Explanations

    specifying types

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

    item type or attribute identification

    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
    ImgBoard
    0.50
     Елена
    0.50
     במהלך
    0.46
     стоимо
    0.45
    漩
    0.43
    Fprintf
    0.43
    AssetsResponse
    0.43
    SqlQuery
    0.43
    <unused82>
    0.43
     رجسٹ
    0.42
    POSITIVE LOGITS
    type
    0.77
     type
    0.75
     types
    0.70
    类型
    0.70
     Loại
    0.65
     Types
    0.64
    Type
    0.61
     Type
    0.61
    タイプ
    0.59
    types
    0.59
    Activations Density 0.014%

    No Known Activations