© 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. 10-GEMMASCOPE-RES-131K
    7. 85871
    Prev
    Next
    INDEX
    Explanations

    elevated psa result

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

    phrases expressing relationships or connections between concepts in explanatory text.

    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_10/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
     like
    -2.17
     at
    -2.08
     for
    -1.91
     so
    -1.84
     From
    -1.81
     all
    -1.78
    :
    -1.76
     most
    -1.72
     mostly
    -1.68
     Like
    -1.64
    POSITIVE LOGITS
    Ꮴ
    1.88
     olabilir
    1.74
     podrán
    1.73
     gruesome
    1.72
     sarà
    1.70
     resultan
    1.69
     můžete
    1.67
    🪛
    1.67
    Toujours
    1.67
    可能会
    1.63
    Activations Density 0.057%

    No Known Activations