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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 118911
    Prev
    Next
    INDEX
    Explanations

    medical and technical terms

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

    cities, locations, and places like "Portland" in legal or formal documents.

    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
    좁
    -0.84
    jenih
    -0.83
    ///**
    -0.83
    Label
    -0.81
    GLenum
    -0.80
    əri
    -0.79
    empuan
    -0.77
    में
    -0.76
    pragma
    -0.76
    SAX
    -0.74
    POSITIVE LOGITS
    cination
    0.93
     interesantes
    0.92
     Versorgung
    0.92
     communiquez
    0.91
     помощью
    0.91
    csolódó
    0.90
    tivo
    0.88
    がとても
    0.88
    Gras
    0.87
    fry
    0.85
    Activations Density 0.001%

    No Known Activations