© 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. 79869
    Prev
    Next
    INDEX
    Explanations

    multiple parts or stages

    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
    都快
    -1.30
     fiasco
    -1.30
     esquecer
    -1.29
     mudança
    -1.27
     semelhante
    -1.25
     zaji
    -1.23
     correto
    -1.22
     adequado
    -1.21
     lembrar
    -1.19
     violência
    -1.19
    POSITIVE LOGITS
     or
    2.13
     funcion
    1.30
     levante
    1.26
     atau
    1.25
     或
    1.23
     nebo
    1.20
     this
    1.18
     There
    1.17
     prome
    1.13
     uffic
    1.12
    Activations Density 0.088%

    No Known Activations