© 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. 45317
    Prev
    Next
    INDEX
    Explanations

    Riverside and Silverstone locations

    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
     The
    -3.56
    en
    -3.55
    {
    -3.50
    _
    -2.69
    ).
    -2.63
    —
    -2.61
    \
    -2.58
    ?
    -2.55
    y
    -2.44
     With
    -2.42
    POSITIVE LOGITS
    ᜀ
    3.41
    獁
    3.27
    ୌ
    3.00
    蜑
    2.97
     fieltro
    2.95
    玧
    2.94
    趼
    2.94
     排骨
    2.88
     otwor
    2.84
    鹟
    2.84
    Activations Density 0.001%

    No Known Activations