© 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. 108445
    Prev
    Next
    INDEX
    Explanations

    software, disease, desire, prevent

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

    file and document metadata in code or markup files.

    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
    которы
    -0.77
     ID
    -0.72
     event
    -0.70
     eligible
    -0.69
    靳
    -0.68
     Bed
    -0.68
     érde
    -0.67
     Event
    -0.66
    bed
    -0.65
     Board
    -0.64
    POSITIVE LOGITS
     Atari
    0.96
    سف
    0.85
    cornerRadius
    0.83
     Corvette
    0.79
    гам
    0.79
    chet
    0.79
    扉
    0.78
    뎐
    0.78
    "];
    0.77
     sarees
    0.77
    Activations Density 0.000%

    No Known Activations