© 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. 34-GEMMASCOPE-RES-131K
    7. 3256
    Prev
    Next
    INDEX
    Explanations

    XHTML doctype declarations

    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_34/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
    brar
    -0.84
     QI
    -0.79
    oughby
    -0.77
     SERVICE
    -0.76
     Draper
    -0.75
    errno
    -0.75
    fabrik
    -0.74
    service
    -0.71
    サービス
    -0.70
     hát
    -0.70
    POSITIVE LOGITS
     Charlie
    0.78
    Charlie
    0.68
    ╱
    0.66
    ggel
    0.64
     Adams
    0.63
     Jamaica
    0.63
    Heap
    0.63
    弊
    0.63
    孔
    0.63
     Tom
    0.62
    Activations Density 0.070%

    No Known Activations