© 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. 84509
    Prev
    Next
    INDEX
    Explanations

    programming code and structures

    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
    s
    -3.39
    at
    -3.13
    h
    -2.94
    er
    -2.52
     o
    -2.42
    k
    -2.38
    m
    -2.36
    name
    -2.34
    AN
    -2.33
    x
    -2.28
    POSITIVE LOGITS
    Artigo
    2.39
     cayó
    2.23
     domés
    2.23
    sandalia
    2.22
    퀼
    2.20
    ჱ
    2.17
     remercie
    2.16
    錞
    2.16
    淠
    2.14
     necesitaba
    2.13
    Activations Density 0.000%

    No Known Activations