© 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. 47869
    Prev
    Next
    INDEX
    Explanations

    directory navigation and git commands

    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
    fread
    -0.84
    кол
    -0.83
    fscanf
    -0.73
     predstav
    -0.73
     Receive
    -0.71
    findViewById
    -0.70
    creva
    -0.70
    パー
    -0.69
    が終わ
    -0.69
    braten
    -0.68
    POSITIVE LOGITS
    cd
    2.14
     cd
    1.94
    chdir
    1.88
     goTo
    1.73
    moveTo
    1.63
     CD
    1.52
    Goto
    1.48
     Goto
    1.47
    goto
    1.46
    Cd
    1.45
    Activations Density 0.063%

    No Known Activations