© 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. 73992
    Prev
    Next
    INDEX
    Explanations

    specificity and selection

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

    text that restricts, narrows, or specifically defines a scope or context.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    elesai
    -0.89
    farlane
    -0.83
    stellar
    -0.80
    続きます
    -0.79
    gründ
    -0.79
    ціє
    -0.79
    evident
    -0.78
    ӿ
    -0.78
     徒歩
    -0.76
    días
    -0.75
    POSITIVE LOGITS
     specific
    1.94
    specific
    1.76
     subset
    1.71
     narrower
    1.63
     narrowed
    1.54
    pecific
    1.52
    เฉพาะ
    1.51
    Specific
    1.50
     spesifik
    1.49
     specifically
    1.48
    Activations Density 0.183%

    No Known Activations