© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 64894
    Prev
    Next
    INDEX
    Explanations

    inf/influ/infla prefix

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

    brand and product names, particularly technical software and pharmaceutical terms.

    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_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
    fractive
    -0.93
    frist
    -0.88
    VERSE
    -0.88
    ନ
    -0.80
     lievito
    -0.78
    лятор
    -0.77
    Isi
    -0.77
     controlado
    -0.77
    ῖς
    -0.77
    kasse
    -0.77
    POSITIVE LOGITS
     Inf
    1.38
    inf
    1.33
     inf
    1.27
     INF
    1.21
     Influ
    1.02
    Inf
    1.01
    INF
    0.85
     Maxwell
    0.85
     Infin
    0.79
     इं
    0.79
    Activations Density 0.039%

    No Known Activations