© 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. 44093
    Prev
    Next
    INDEX
    Explanations

    authoritative, definitive, canonical, authenticated

    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
     \"
    -2.83
    赑
    -2.61
    ním
    -2.30
    )
    -2.22
     ''
    -2.16
     думал
    -2.14
     conocido
    -2.13
     '
    -2.11
     heiligen
    -2.11
     If
    -2.09
    POSITIVE LOGITS
    艫
    2.55
    焌
    2.48
     authoritative
    2.47
    
    2.45
    杙
    2.41
    銛
    2.39
    
    2.39
     作り方
    2.39
    </b>
    2.39
    ೬
    2.38
    Activations Density 0.000%

    No Known Activations