© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 102258
    Prev
    Next
    INDEX
    Explanations

    code delimiters and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite

    language-specific syntax for function/method parameter lists and annotations, particularly parentheses following class names, decorators, or type declarations.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     there
    -1.62
     Then
    -1.55
    痦
    -1.46
     גם
    -1.44
     theres
    -1.40
     then
    -1.38
     when
    -1.38
    付けた
    -1.35
    取った
    -1.34
     When
    -1.31
    POSITIVE LOGITS
    袿
    1.36
    其中
    1.29
     meilleurs
    1.24
    siehe
    1.23
     kablo
    1.23
    ო
    1.23
     magnifiques
    1.23
     Aucun
    1.21
    }=\
    1.21
    舒服
    1.20
    Activations Density 0.008%

    No Known Activations