© 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. 67955
    Prev
    Next
    INDEX
    Explanations

    title of organization or role

    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
    pptx
    -1.32
    ってます
    -1.31
    SOU
    -1.29
    schwe
    -1.27
     (~(
    -1.27
     största
    -1.26
     نسبة
    -1.25
    heh
    -1.25
     berühm
    -1.24
     BELIEVE
    -1.23
    POSITIVE LOGITS
     if
    1.27
     at
    1.23
     all
    1.22
     you
    1.22
    In
    1.21
     will
    1.18
    ınıza
    1.17
    7
    1.17
     even
    1.17
    multicolumn
    1.11
    Activations Density 0.038%

    No Known Activations