© 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. 71296
    Prev
    Next
    INDEX
    Explanations

    email domain names

    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
    !!!!!!!
    -1.88
    鐿
    -1.76
    .........
    -1.69
    !!!!!!!!!!
    -1.69
     💖
    -1.67
    !!!!!!!!
    -1.66
    !!!!!!!!!
    -1.66
    .............
    -1.64
    ............
    -1.63
    !!!!!!
    -1.63
    POSITIVE LOGITS
     having
    1.77
    としては
    1.76
     certainly
    1.73
     can
    1.70
     definitely
    1.70
     Grundstück
    1.68
     attempting
    1.63
     formally
    1.61
     adapting
    1.61
     stated
    1.60
    Activations Density 0.021%

    No Known Activations