© 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. 86449
    Prev
    Next
    INDEX
    Explanations

    database update queries

    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
    ↵↵
    -2.77
    ).
    -2.58
    a
    -2.34
    1
    -2.30
    -
    -2.19
     The
    -2.17
    /
    -2.16
    (
    -2.00
     '
    -1.98
      
    -1.91
    POSITIVE LOGITS
    鲼
    2.30
     strane
    2.27
    ￬
    2.13
    縂
    2.05
    ﾒ
    1.99
     maniere
    1.97
     circon
    1.96
    jedno
    1.96
     penser
    1.95
     tedesco
    1.95
    Activations Density 0.003%

    No Known Activations