© 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. 34-GEMMASCOPE-RES-131K
    7. 109566
    Prev
    Next
    INDEX
    Explanations

    code snippets and data structures

    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
    getPassword
    -0.69
    liters
    -0.66
    subequations
    -0.65
    Trav
    -0.64
     any
    -0.63
    Pick
    -0.62
     TODO
    -0.62
     pick
    -0.62
     backing
    -0.61
    laway
    -0.61
    POSITIVE LOGITS
     Jank
    0.77
    íqu
    0.71
    寝る
    0.69
     Rector
    0.69
    ocyan
    0.69
    Laravel
    0.69
     Chỉ
    0.69
     ASSOCIATED
    0.68
     CLK
    0.68
    omin
    0.68
    Activations Density 0.060%

    No Known Activations