© 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. 49525
    Prev
    Next
    INDEX
    Explanations

    motor protein transport

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

    biology and cellular biology terms, especially related to proteins, cellular transportation, and molecular movement.

    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
     Zap
    -0.87
     bake
    -0.73
    oną
    -0.72
    }:$
    -0.71
    rijf
    -0.71
    】：
    -0.70
    裕
    -0.70
    স্
    -0.69
    getY
    -0.68
    BANK
    -0.68
    POSITIVE LOGITS
     motors
    1.41
     motor
    1.13
    motors
    1.00
     proces
    0.98
     Motors
    0.96
    Motors
    0.93
     kines
    0.91
    motor
    0.87
     retrograde
    0.85
    NoStop
    0.84
    Activations Density 0.062%

    No Known Activations