© 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. 38623
    Prev
    Next
    INDEX
    Explanations

    legal restrictions and exceptions

    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
     tratamento
    -1.23
     rowspan
    -1.18
    他也
    -1.15
    ;
    -1.11
    álise
    -1.11
    ýchod
    -1.08
     posibles
    -1.08
     antemano
    -1.05
     will
    -1.03
     sierpnia
    -1.03
    POSITIVE LOGITS
     навіть
    1.31
    ಅ
    1.25
    ＞＞
    1.20
    Especificações
    1.16
    Even
    1.16
    Spesifikasi
    1.16
    timately
    1.13
    ಎ
    1.13
    hibitions
    1.13
     Especific
    1.11
    Activations Density 0.054%

    No Known Activations