© 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. 43742
    Prev
    Next
    INDEX
    Explanations

    arrested, rightful owners, or status bar

    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
     worries
    -2.92
     has
    -2.81
     If
    -2.73
    ﾛ
    -2.66
    }
    -2.59
     aspire
    -2.53
    甦
    -2.50
     Both
    -2.44
    狹
    -2.42
    狨
    -2.42
    POSITIVE LOGITS
    ’
    3.56
    s
    2.91
    ized
    2.63
    皤
    2.63
     ſich
    2.55
    羮
    2.53
    酲
    2.52
    ⬮
    2.50
     ‚
    2.44
     cial
    2.36
    Activations Density 0.016%

    No Known Activations