© 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. 70646
    Prev
    Next
    INDEX
    Explanations

    permissions and conditions

    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
    Смотрите
    -1.20
    なんと
    -1.13
    }{#
    -1.12
    ของ
    -1.11
     construção
    -1.10
     localização
    -1.09
     suspensão
    -1.08
    caucasian
    -1.08
     iluminação
    -1.08
     ejecución
    -1.08
    POSITIVE LOGITS
     or
    1.83
     including
    1.45
     any
    1.34
     either
    1.19
     If
    1.11
    either
    1.09
     except
    1.07
    even
    1.07
     либо
    1.06
     nor
    1.04
    Activations Density 0.026%

    No Known Activations