© 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. 32949
    Prev
    Next
    INDEX
    Explanations

    Vascular smooth muscle knee Total

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

    words and names associated with South Indian places, particularly locations in Kerala and Karnataka.

    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
    Kek
    -0.75
    Ін
    -0.73
    ConfigFile
    -0.73
    usky
    -0.73
     locate
    -0.71
    Сти
    -0.69
    locating
    -0.68
    คิด
    -0.68
    acionales
    -0.67
     crainte
    -0.67
    POSITIVE LOGITS
    matt
    0.77
    $<
    0.76
    Temple
    0.75
     CORPORATION
    0.75
     River
    0.75
     apoder
    0.74
    alium
    0.74
    ัติ
    0.73
    hart
    0.72
     temple
    0.71
    Activations Density 0.020%

    No Known Activations