© 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. 112251
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with variables

    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
    鹛
    -2.58
    呶
    -2.44
     torba
    -2.36
    縠
    -2.27
    鼉
    -2.20
     }));
    -2.20
    .
    -2.20
    𓋼
    -2.17
    ')}}">
    -2.17
    Ꮵ
    -2.16
    POSITIVE LOGITS
     of
    2.88
     grossen
    2.13
     wth
    2.09
     fomentar
    2.06
    他还
    1.98
    ,
    1.95
    又は
    1.90
    及び
    1.86
     visibilité
    1.84
    之际
    1.81
    Activations Density 0.096%

    No Known Activations