© 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. 72694
    Prev
    Next
    INDEX
    Explanations

    subject of a post

    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
    ngulo
    -1.72
     artig
    -1.48
    viene
    -1.48
     設計
    -1.44
    ซึ่ง
    -1.38
    ië
    -1.37
    cijos
    -1.36
    fæ
    -1.36
     અને
    -1.35
     století
    -1.35
    POSITIVE LOGITS
     most
    2.00
     both
    1.95
     every
    1.93
     people
    1.81
    eeeeeeee
    1.80
     these
    1.77
     
    1.77
    eeeee
    1.72
     more
    1.71
     After
    1.71
    Activations Density 0.041%

    No Known Activations