© 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. 34-GEMMASCOPE-RES-131K
    7. 59231
    Prev
    Next
    INDEX
    Explanations

    must reproduce

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

    code license text and legal statements, particularly in software 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
    нос
    -0.68
     dáng
    -0.67
    ğı
    -0.67
     Volvo
    -0.66
    adda
    -0.66
     behind
    -0.66
     bakom
    -0.66
    がて
    -0.66
     Famille
    -0.66
     Charlie
    -0.64
    POSITIVE LOGITS
     approche
    0.74
    ̀n
    0.74
    approche
    0.72
     総
    0.72
    ⎫
    0.71
    잔
    0.70
    heon
    0.69
    ctus
    0.69
     Meier
    0.69
    sugar
    0.68
    Activations Density 0.046%

    No Known Activations