© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 2607
    Prev
    Next
    INDEX
    Explanations

    MODULE numbers

    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
     चीज़
    -2.16
    ਗ਼
    -2.09
    ਖ਼
    -2.09
    क़
    -1.82
    ख़
    -1.67
     „
    -1.60
    ‟
    -1.60
     ".";
    -1.55
     ſ
    -1.48
    ţiei
    -1.38
    POSITIVE LOGITS
    莴
    1.61
     Eſ
    1.57
    兩
    1.55
    ſo
    1.48
    立
    1.39
    零食
    1.34
     Theſe
    1.30
    baarheid
    1.27
     Ã
    1.25
    利
    1.23
    Activations Density 9.684%

    No Known Activations