© 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. 39575
    Prev
    Next
    INDEX
    Explanations

    prefixes like open-

    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
     
    -3.88
    er
    -3.33
    {
    -3.30
    C
    -3.25
    ’
    -3.22
    S
    -3.19
    T
    -3.13
    M
    -2.97
    P
    -2.97
    le
    -2.94
    POSITIVE LOGITS
     یا
    3.33
    quelize
    3.22
    鰱
    3.11
     или
    3.06
     аккура
    2.98
    屜
    2.98
    ésil
    2.92
    ftrag
    2.81
    的吗
    2.81
    Tahun
    2.80
    Activations Density 0.052%

    No Known Activations