© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 101628
    Prev
    Next
    INDEX
    Explanations

    news and event coverage

    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
    '
    -1.80
    *
    -1.78
    ”
    -1.70
     Creating
    -1.61
    </h1>
    -1.59
    "
    -1.52
     three
    -1.46
     Going
    -1.45
     —
    -1.42
    ↵↵
    -1.41
    POSITIVE LOGITS
    渽
    1.92
    ㈲
    1.71
     
    1.70
     acque
    1.70
     apparente
    1.66
     anlay
    1.64
    蘼
    1.63
     bureaux
    1.63
    唞
    1.63
    と思いますが
    1.62
    Activations Density 0.015%

    No Known Activations