© 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. 118671
    Prev
    Next
    INDEX
    Explanations

    Keywords, Population, Allergy

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

    programming-related elements like method names, file paths, code syntax, and technical documentation.

    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
    ঋ
    -0.65
     congrat
    -0.63
    maid
    -0.61
     FINISH
    -0.61
     Specials
    -0.60
     Prest
    -0.60
    我觉得
    -0.60
    jutant
    -0.60
    ñor
    -0.59
    KIT
    -0.59
    POSITIVE LOGITS
     sheath
    0.65
    ʂ
    0.64
    auer
    0.64
    chtenstein
    0.62
     setShow
    0.62
     Ryder
    0.61
    LoadData
    0.60
     zw
    0.60
     Chlorine
    0.60
    Rose
    0.60
    Activations Density 0.083%

    No Known Activations