© 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. 102590
    Prev
    Next
    INDEX
    Explanations

    completed studies

    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
    }
    -2.70
    )
    -2.56
    ’
    -2.50
    '
    -2.45
    可以
    -2.44
    </i>
    -2.39
    一旁
    -2.25
    2
    -2.20
    !!!!!!
    -2.17
    </h1>
    -2.14
    POSITIVE LOGITS
    齷
    2.86
    
    2.75
     глазах
    2.63
    浤
    2.61
    霂
    2.52
    唿
    2.42
    ХОД
    2.39
    焌
    2.39
     стене
    2.34
    摭
    2.34
    Activations Density 0.003%

    No Known Activations