© 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. 99885
    Prev
    Next
    INDEX
    Explanations

    brain, electrically, vital

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

    words related to physical or scientific phenomena, particularly substances, matter, and energy.

    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
    Penulis
    -0.84
     gamma
    -0.77
     behaviour
    -0.75
    обре
    -0.75
    ladesh
    -0.73
     behavior
    -0.73
    诱
    -0.73
    Ἱ
    -0.73
    禰
    -0.72
    fır
    -0.71
    POSITIVE LOGITS
    action
    0.90
     renovating
    0.90
     renovation
    0.87
     album
    0.85
     action
    0.84
     seleccionamos
    0.84
    Nutrition
    0.84
    尚未
    0.84
     renovations
    0.81
    ochemical
    0.79
    Activations Density 0.011%

    No Known Activations