© 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. 10-GEMMASCOPE-RES-131K
    7. 130685
    Prev
    Next
    INDEX
    Explanations

    what's like X or just X

    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_10/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
     všetkých
    -1.59
     miljoner
    -1.37
     who
    -1.37
     ľah
    -1.36
     svoju
    -1.34
     ingrédients
    -1.33
     médicaments
    -1.31
     rých
    -1.31
     tých
    -1.31
     všetky
    -1.30
    POSITIVE LOGITS
     a
    1.57
     there
    1.37
     otra
    1.23
    wanzig
    1.20
     teniendo
    1.16
    otomy
    1.14
    เกี่ยว
    1.14
    僥
    1.12
    紘
    1.12
     an
    1.11
    Activations Density 0.018%

    No Known Activations