© 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. 100446
    Prev
    Next
    INDEX
    Explanations

    javascript or shell commands

    np_acts-logits-general · gemini-2.5-flash-lite

    opening code tags in markup and documentation files.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
    </h2>
    -3.00
    ing
    -2.33
    ξης
    -2.20
    ୌ
    -2.14
    言えば
    -2.08
    횃
    -2.06
    }
    -2.05
    ``
    -2.02
     einer
    -2.02
    ੝
    -1.99
    POSITIVE LOGITS
    鄚
    2.30
    榦
    2.28
    >
    2.27
    鲠
    2.25
     spiele
    2.00
     vengono
    1.94
    塒
    1.92
     quantità
    1.92
     juft
    1.91
    یریت
    1.91
    Activations Density 0.002%

    No Known Activations