© 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. 4260
    Prev
    Next
    INDEX
    Explanations

    script followed by do, MDA followed by mb

    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
     eſt
    -0.78
    rins
    -0.77
     vedette
    -0.72
    velopment
    -0.70
    拡張
    -0.68
    loed
    -0.68
    stained
    -0.68
    ζί
    -0.68
    hits
    -0.68
    Venus
    -0.68
    POSITIVE LOGITS
     Imper
    0.66
    brium
    0.63
     durfte
    0.62
    诩
    0.60
    ся
    0.60
    Child
    0.59
     коман
    0.59
     tap
    0.58
    xoxo
    0.58
    muñeca
    0.58
    Activations Density 0.070%

    No Known Activations