© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 60580
    Prev
    Next
    INDEX
    Explanations

    mark your calendars now

    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
     to
    -1.60
     variously
    -1.56
    ❮
    -1.54
    érieures
    -1.48
     unwelcome
    -1.45
     MUCH
    -1.45
    ⛅
    -1.39
    異なる
    -1.38
    啄
    -1.38
    〖
    -1.38
    POSITIVE LOGITS
    </strong>
    2.30
    on
    1.76
    from
    1.73
    俢
    1.61
    "
    1.61
     farmacé
    1.59
     estómago
    1.58
    >−</
    1.57
     שהוא
    1.56
    ࿆
    1.56
    Activations Density 0.004%

    No Known Activations