© 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. 78288
    Prev
    Next
    INDEX
    Explanations

    command line arguments

    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
    encyclo
    -0.77
    んでる
    -0.77
    ственного
    -0.77
     yhte
    -0.77
     communications
    -0.76
     dentista
    -0.76
    ച്ച
    -0.75
    rups
    -0.75
    datagrid
    -0.75
     Bücher
    -0.74
    POSITIVE LOGITS
    argv
    2.64
     argv
    2.64
     args
    1.91
    ARGV
    1.74
    argc
    1.71
     argc
    1.69
    args
    1.68
     argument
    1.68
     arguments
    1.55
     Argument
    1.53
    Activations Density 0.038%

    No Known Activations