© 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. 127897
    Prev
    Next
    INDEX
    Explanations

    programming keywords and types

    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
     
    -2.11
     hará
    -1.98
    察觉
    -1.96
    はもちろん
    -1.88
     vuelve
    -1.87
     stej
    -1.79
    を作る
    -1.77
     eerst
    -1.77
    それにしても
    -1.76
     großem
    -1.76
    POSITIVE LOGITS
     this
    2.06
    蛧
    1.87
     such
    1.86
    和
    1.83
    焢
    1.77
     these
    1.75
     when
    1.73
     a
    1.73
     potentially
    1.64
     Giochi
    1.63
    Activations Density 0.003%

    No Known Activations