© 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. 76890
    Prev
    Next
    INDEX
    Explanations

    Grateful Dead, Arachidonic acid

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

    grammatically incorrect or awkwardly constructed 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_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
    dokument
    -0.94
    嚐
    -0.93
    精致
    -0.93
    癱
    -0.93
     sillas
    -0.92
    entretien
    -0.90
    LVANIA
    -0.89
     allerlei
    -0.88
    哭了
    -0.87
     PAPERS
    -0.86
    POSITIVE LOGITS
     Yep
    0.88
     to
    0.85
     |
    0.83
     possibilité
    0.80
    ·
    0.74
     chrétiens
    0.73
     smoothly
    0.71
     truthfully
    0.70
    וץ
    0.70
    理由
    0.70
    Activations Density 0.005%

    No Known Activations