© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 86894
    Prev
    Next
    INDEX
    Explanations

    code objects or specific entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    n
    -3.61
    at
    -3.14
    you
    -2.77
    as
    -2.69
    <em>
    -2.69
    x
    -2.67
    <strong>
    -2.64
    to
    -2.61
    You
    -2.61
    or
    -2.56
    POSITIVE LOGITS
    驺
    2.75
    
    2.73
    搥
    2.70
    饹
    2.67
     dezelve
    2.66
    襠
    2.64
    錸
    2.61
    骘
    2.61
    鉏
    2.59
    豨
    2.56
    Activations Density 0.000%

    No Known Activations