© 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. 34-GEMMASCOPE-RES-131K
    7. 118817
    Prev
    Next
    INDEX
    Explanations

    author name

    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_34/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
     Alipay
    -0.84
     Comentarios
    -0.79
     voorzien
    -0.77
     Ciné
    -0.74
    RDF
    -0.73
    édrale
    -0.73
     оценки
    -0.73
    Források
    -0.73
    carousel
    -0.73
    utti
    -0.73
    POSITIVE LOGITS
     respectfully
    1.95
     respectful
    1.70
     salute
    1.59
    Respectfully
    1.32
     saluted
    1.31
     sal
    1.26
     cu
    1.26
    respect
    1.17
     clasped
    1.16
     reporting
    1.06
    Activations Density 0.004%

    No Known Activations