© 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. 75667
    Prev
    Next
    INDEX
    Explanations

    electrical action potentials

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

    content related to neuroscience, particularly focusing on neurons, action potentials, and electrical signaling in the nervous system.

    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
     радиа
    -0.83
     enfrenta
    -0.76
    ticles
    -0.74
     Epist
    -0.71
    ternal
    -0.71
    objects
    -0.69
     reappeared
    -0.69
    輻
    -0.69
    כט
    -0.68
    dcterms
    -0.67
    POSITIVE LOGITS
     depolar
    1.47
     impulse
    1.41
     impulses
    1.32
     electrical
    1.27
     firing
    1.25
     sodium
    1.19
     Impulse
    1.15
    Impulse
    1.15
     propagation
    1.13
     propagate
    1.13
    Activations Density 0.095%

    No Known Activations