© 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. 102681
    Prev
    Next
    INDEX
    Explanations

    angels and demons

    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
    --"
    -1.37
    人工智能
    -1.36
     perak
    -1.32
     jardim
    -1.28
    2
    -1.27
     AGRE
    -1.26
     humiliated
    -1.26
    ..."
    -1.26
    line
    -1.25
    拷
    -1.25
    POSITIVE LOGITS
    (;;)
    1.44
    bandcamp
    1.36
    なの
    1.34
     istnieje
    1.33
    كز
    1.33
    olische
    1.30
     from
    1.30
     wzór
    1.30
     there
    1.29
     nowo
    1.29
    Activations Density 0.019%

    No Known Activations