© 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. 47579
    Prev
    Next
    INDEX
    Explanations

    system file paths and specific keywords

    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
    Royaume
    -0.81
     NCC
    -0.74
     rhino
    -0.74
    parsedMessage
    -0.71
    onesia
    -0.71
    olidation
    -0.69
    tigo
    -0.69
     hatred
    -0.69
     laajenta
    -0.68
     كانت
    -0.68
    POSITIVE LOGITS
     file
    1.34
    proc
    1.28
     proc
    1.27
     sys
    1.26
    sys
    1.20
     files
    1.12
    FILE
    1.07
    Proc
    1.06
    PROC
    1.06
    file
    1.02
    Activations Density 0.024%

    No Known Activations