© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 54197
    Prev
    Next
    INDEX
    Explanations

    walk or approach

    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
    upné
    -0.94
    httpMethod
    -0.85
     עבודה
    -0.83
    izando
    -0.77
    掉了
    -0.76
     вниз
    -0.73
     попу
    -0.72
     slika
    -0.72
    arikan
    -0.72
     DRIVER
    -0.72
    POSITIVE LOGITS
     walked
    3.53
     walk
    3.53
     walks
    3.03
     walking
    2.92
    walk
    2.80
     approach
    2.77
    Walk
    2.69
     approached
    2.69
     Walk
    2.56
     approaches
    2.41
    Activations Density 0.015%

    No Known Activations