© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 14390
    Prev
    Next
    INDEX
    Explanations

    Book, Discussion

    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_22/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
     how
    -1.38
    匾
    -1.32
     what
    -1.30
     kompetisi
    -1.30
     hablaba
    -1.25
     яйцо
    -1.25
     enables
    -1.20
    Erfolge
    -1.17
     dikutip
    -1.17
     allows
    -1.17
    POSITIVE LOGITS
    ++)
    1.23
     gouttes
    1.12
    櫪
    1.09
     opulent
    1.07
     чув
    1.05
     cardin
    1.05
     diferente
    1.05
     diferentes
    1.04
    设计师
    1.02
     dau
    1.02
    Activations Density 0.002%

    No Known Activations