© 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. 129078
    Prev
    Next
    INDEX
    Explanations

    describing layers

    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
    瓩
    -2.36
    ühungen
    -2.33
     zelo
    -2.27
    indelijk
    -2.20
    无比
    -2.17
    ℣
    -2.14
     Estadística
    -2.13
    s
    -2.13
     There
    -2.09
     pomen
    -2.09
    POSITIVE LOGITS
    沨
    2.67
    玙
    2.47
     лишь
    2.25
    思索
    2.23
     они
    2.20
    not
    2.19
    我一
    2.16
     ilość
    2.14
     ‚
    2.09
     dalších
    2.09
    Activations Density 0.006%

    No Known Activations