© 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. 58584
    Prev
    Next
    INDEX
    Explanations

    url strings in code

    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
     Khusus
    -1.55
    řit
    -1.45
    </b>
    -1.45
     Hidup
    -1.41
    :[{
    -1.33
    .“
    -1.33
     loca
    -1.30
    kirakan
    -1.30
     Pakai
    -1.29
     Jangan
    -1.28
    POSITIVE LOGITS
     \
    1.68
     September
    1.57
     any
    1.52
    ใด
    1.36
    com
    1.32
    ⿱
    1.31
    PLEMENT
    1.31
    瀋
    1.27
    ⿰
    1.27
    \
    1.25
    Activations Density 0.024%

    No Known Activations