© 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. 128730
    Prev
    Next
    INDEX
    Explanations

    UI and interface elements

    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
     mutta
    -1.63
     ottimo
    -1.63
     jotka
    -1.49
    ਞ
    -1.48
     ImportError
    -1.47
    väll
    -1.38
    hkern
    -1.38
     ſy
    -1.38
     joka
    -1.36
    ];
    -1.34
    POSITIVE LOGITS
    ↵↵
    1.70
     /
    1.52
    軋
    1.43
    .
    1.42
     all
    1.34
    饗
    1.28
    禿
    1.24
    Бли
    1.19
    Transcripción
    1.18
     where
    1.12
    Activations Density 0.028%

    No Known Activations