© 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. 99138
    Prev
    Next
    INDEX
    Explanations

    number of views

    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
    」「
    -1.63
     subwoofer
    -1.48
    will
    -1.46
     以上
    -1.45
     sedia
    -1.45
    ”?
    -1.42
     carbur
    -1.41
    ”,
    -1.40
    "});
    -1.40
     pusi
    -1.39
    POSITIVE LOGITS
     on
    1.72
     Gefäng
    1.53
     '
    1.48
    '
    1.45
     biß
    1.45
    uchungen
    1.38
     perdiendo
    1.36
     quedarse
    1.35
          
    1.34
     württemberg
    1.32
    Activations Density 0.028%

    No Known Activations