© 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. 11547
    Prev
    Next
    INDEX
    Explanations

    siguiente, seguir, sedentary

    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
    the
    -2.69
    ارتمان
    -2.58
    d
    -2.55
    鵟
    -2.50
    a
    -2.50
    讠
    -2.38
    付ける
    -2.31
    mathrm
    -2.30
    珝
    -2.25
    days
    -2.23
    POSITIVE LOGITS
    нию
    2.56
    weakSelf
    2.47
     ของ
    2.44
     所以
    2.36
     -
    2.34
    ."
    2.33
    ва
    2.28
    in
    2.25
     hes
    2.25
    ная
    2.20
    Activations Density 0.003%

    No Known Activations