© 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. 22-GEMMASCOPE-RES-131K
    7. 35711
    Prev
    Next
    INDEX
    Explanations

    volume/weight percentage and ratio

    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
    StoryboardSegue
    -1.18
    impulan
    -1.14
    先日
    -1.13
    itology
    -1.08
     splet
    -1.06
     $("<
    -1.06
    涠
    -1.06
    疍
    -1.06
    私たちは
    -1.06
    Ngoài
    -1.06
    POSITIVE LOGITS
     of
    1.48
    嘞
    1.14
    lerinde
    1.02
    ju
    1.00
    ENIA
    1.00
    ak
    0.99
    ficie
    0.97
    СКИ
    0.97
     speaking
    0.96
    ？
    0.96
    Activations Density 0.015%

    No Known Activations