© 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. 10-GEMMASCOPE-RES-131K
    7. 105172
    Prev
    Next
    INDEX
    Explanations

    programming code keywords

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

    code in statically-typed programming languages, particularly class and method declarations with type annotations.

    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
     Propiedad
    -1.21
     Giochi
    -1.20
     caráter
    -1.18
     évidemment
    -1.17
     hugely
    -1.15
    hören
    -1.14
     nötig
    -1.13
     crucial
    -1.13
     refuer
    -1.13
     aluno
    -1.12
    POSITIVE LOGITS
     علاوه
    1.21
     thither
    1.15
    {}/
    1.12
     शुर
    1.10
    tizado
    1.09
     around
    1.09
     nejen
    1.08
     intricacies
    1.07
    ichtete
    1.05
    发布时间
    1.05
    Activations Density 0.110%

    No Known Activations