© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 86906
    Prev
    Next
    INDEX
    Explanations

    soap, cartoons, Pokemon

    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
    м
    -3.27
    л
    -2.70
    "
    -2.67
     "
    -2.45
    ه
    -2.34
    (
    -2.33
     was
    -2.27
    麈
    -2.27
    \
    -2.22
    year
    -2.20
    POSITIVE LOGITS
    羮
    2.69
     głó
    2.69
    所谓的
    2.64
    翆
    2.61
    凩
    2.58
    ⬮
    2.50
    </strong>
    2.39
    schon
    2.34
    荩
    2.27
    獁
    2.27
    Activations Density 0.006%

    No Known Activations