© 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. 106873
    Prev
    Next
    INDEX
    Explanations

    sudo and shell 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
     ff
    -0.86
     Galaxy
    -0.82
    older
    -0.81
     Attach
    -0.81
     NW
    -0.77
     Candy
    -0.75
    Ferrari
    -0.75
     Dry
    -0.73
     NSW
    -0.72
     มี
    -0.72
    POSITIVE LOGITS
    sed
    1.09
     sed
    0.94
     sudor
    0.85
    앓
    0.77
     opio
    0.75
     echo
    0.75
    echo
    0.74
     ferti
    0.74
     SED
    0.73
     Pamphlet
    0.73
    Activations Density 0.060%

    No Known Activations