© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 31983
    Prev
    Next
    INDEX
    Explanations

    take effect

    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
    Ẻ
    -0.95
    OrCreate
    -0.75
    
    -0.72
    kuva
    -0.71
     azért
    -0.71
     Grown
    -0.69
    cherichia
    -0.68
    inario
    -0.68
    )}^{
    -0.67
     acquaintance
    -0.66
    POSITIVE LOGITS
     take
    3.00
     takes
    2.88
     took
    2.70
    take
    2.44
    Take
    2.36
    takes
    2.31
     taking
    2.28
     effective
    2.17
     Take
    2.16
     Takes
    2.11
    Activations Density 0.043%

    No Known Activations