© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 76251
    Prev
    Next
    INDEX
    Explanations

    All rights reserved

    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
    чают
    -0.88
     Schwar
    -0.78
    ură
    -0.72
    圍
    -0.70
    ߣ
    -0.70
    uito
    -0.69
    REWRITE
    -0.68
    빴
    -0.67
     Cochin
    -0.67
     geta
    -0.65
    POSITIVE LOGITS
    Section
    0.71
     dinosaurios
    0.68
     Section
    0.68
     silver
    0.68
    rosted
    0.67
    cp
    0.65
    skb
    0.65
     atypical
    0.65
     ceramics
    0.64
     Partition
    0.63
    Activations Density 0.037%

    No Known Activations