© 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. 102753
    Prev
    Next
    INDEX
    Explanations

    lucky enough

    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
    .},
    -1.49
    iorno
    -1.45
    赅
    -1.38
     родствен
    -1.38
    umente
    -1.37
    ٫
    -1.35
    鲧
    -1.34
    涑
    -1.32
    ？！”
    -1.32
    簡単な
    -1.31
    POSITIVE LOGITS
     with
    1.76
     hubiese
    1.63
     but
    1.41
     setelan
    1.41
     pudiera
    1.39
    However
    1.38
     pueda
    1.38
     quede
    1.36
     แต่
    1.35
    ).
    1.34
    Activations Density 0.006%

    No Known Activations