© 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. 31062
    Prev
    Next
    INDEX
    Explanations

    file or path 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
    saver
    -0.94
     saving
    -0.87
    mkdir
    -0.84
    subdir
    -0.81
     mkdir
    -0.81
    exporter
    -0.79
     save
    -0.77
    stackoverflow
    -0.73
     internal
    -0.73
    ركات
    -0.71
    POSITIVE LOGITS
     input
    1.62
    INPUT
    1.23
     infile
    1.22
    入力
    1.20
    input
    1.19
     file
    1.15
    输入
    1.15
     getInput
    1.09
    ConfigFile
    1.09
    Input
    1.09
    Activations Density 0.046%

    No Known Activations