© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 7247
    Prev
    Next
    INDEX
    Explanations

    opening quote

    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
     scrutin
    -2.75
    焄
    -2.70
     s
    -2.47
    They
    -2.47
    it
    -2.45
    ↵
    -2.44
     exorbitant
    -2.41
    釦
    -2.33
    憤
    -2.33
    <bos>
    -2.30
    POSITIVE LOGITS
    鲠
    3.28
    颪
    3.23
     Then
    2.75
     PLAYERS
    2.73
    鮡
    2.72
    埽
    2.58
    歘
    2.55
    蹕
    2.55
    a
    2.52
     prezen
    2.47
    Activations Density 0.001%

    No Known Activations