© 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. 54245
    Prev
    Next
    INDEX
    Explanations

    come back together

    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
    idez
    -0.77
    ‰
    -0.77
    cmu
    -0.76
    rollers
    -0.73
    つは
    -0.73
    olateral
    -0.71
    ocat
    -0.71
    stk
    -0.70
     Weber
    -0.70
     gwar
    -0.69
    POSITIVE LOGITS
     full
    4.28
    full
    3.31
    Full
    3.11
     circle
    2.86
     Full
    2.81
    FULL
    2.70
    circle
    2.44
     peł
    2.38
     FULL
    2.33
    Circle
    2.25
    Activations Density 0.023%

    No Known Activations