© 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. 71385
    Prev
    Next
    INDEX
    Explanations

    forces

    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
     '
    -3.69
     WITH
    -2.48
     \"
    -2.45
    “
    -2.39
    with
    -2.27
    𐄁
    -2.27
    ',
    -2.25
    \
    -2.23
    をしていた
    -2.20
    щита
    -2.11
    POSITIVE LOGITS
    ?’
    2.77
    ’,
    2.77
    肫
    2.55
    ’-
    2.48
    ’:
    2.48
    !’
    2.47
    ’;
    2.41
    钲
    2.36
    लों
    2.34
    ’.
    2.25
    Activations Density 0.004%

    No Known Activations