© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 12151
    Prev
    Next
    INDEX
    Explanations

    structural elements

    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
     or
    -1.62
     and
    -1.23
     by
    -1.19
     any
    -1.19
     as
    -1.19
     if
    -1.10
     in
    -1.07
     usually
    -1.05
     an
    -1.04
     what
    -1.01
    POSITIVE LOGITS
     Insgesamt
    1.17
     प्रत्येक
    1.11
     mercredi
    1.09
     diseñado
    1.08
     Nuestro
    1.06
     Saludos
    1.05
     Aquí
    1.04
     Quiero
    1.03
    鶺
    1.02
     desenho
    1.02
    Activations Density 0.074%

    No Known Activations