© 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. 34-GEMMASCOPE-RES-131K
    7. 60743
    Prev
    Next
    INDEX
    Explanations

    code generation

    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
     teste
    -0.93
     STER
    -0.91
     INNOV
    -0.91
    煨
    -0.91
     BIBLE
    -0.90
     MOON
    -0.90
     BUILT
    -0.89
     erreurs
    -0.88
     วิ
    -0.88
     THUR
    -0.87
    POSITIVE LOGITS
     from
    1.45
     generate
    1.30
     tools
    1.29
     generates
    1.28
     generator
    1.20
     on
    1.17
     tool
    1.16
     generating
    1.10
     using
    1.09
    generator
    1.09
    Activations Density 0.082%

    No Known Activations