© 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. 58308
    Prev
    Next
    INDEX
    Explanations

    random variables and walks

    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
    ประ
    -0.78
     randomised
    -0.77
     randomization
    -0.73
    SOL
    -0.73
    宝
    -0.70
     apprehen
    -0.70
    륨
    -0.69
     caribou
    -0.68
     Freedman
    -0.68
    ходя
    -0.68
    POSITIVE LOGITS
     variables
    1.20
     field
    0.94
    variables
    0.92
     walk
    0.91
     experiment
    0.90
     fields
    0.87
     Field
    0.84
     bancada
    0.82
     Walk
    0.82
    试验
    0.81
    Activations Density 0.036%

    No Known Activations