© 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. 47587
    Prev
    Next
    INDEX
    Explanations

    code keywords and syntax

    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
    んだろう
    -1.12
    の地
    -1.09
     of
    -1.08
    の方に
    -1.08
    ことになる
    -1.06
    の方も
    -1.05
    になれる
    -1.04
    PageModule
    -1.03
    proved
    -1.02
    的で
    -1.02
    POSITIVE LOGITS
    ↵
    1.30
    時間は
    1.05
    を
    0.98
    岁的
    0.94
    ตู
    0.92
     nothing
    0.91
    各種
    0.90
    ＆
    0.90
    ？！
    0.89
     see
    0.87
    Activations Density 0.007%

    No Known Activations