© 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. 1996
    Prev
    Next
    INDEX
    Explanations

    names starting with 'Z' or 'Zac'/'Zack'

    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
    гают
    -0.75
    ところは
    -0.75
    Ancien
    -0.74
    relatively
    -0.74
    delt
    -0.72
     தே
    -0.71
    Rudi
    -0.71
    Opal
    -0.71
     забу
    -0.70
    spooky
    -0.69
    POSITIVE LOGITS
     Z
    1.05
    Z
    0.86
     workday
    0.76
    面前
    0.75
    keras
    0.75
     z
    0.73
     особенности
    0.73
    例
    0.73
     ZAP
    0.73
    ativity
    0.73
    Activations Density 0.102%

    No Known Activations