© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77806
    Prev
    Next
    INDEX
    Explanations

    Degree of, such as, Health-related

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

    product specifications and numerical measurements in technical documents and product listings.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron fires strongly on multi‐word proper names and titles—especially brand and model names or document headings.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    Guan
    -0.73
    ❂
    -0.72
    fingerprint
    -0.72
     府
    -0.72
     Guan
    -0.70
     inconsistency
    -0.69
     ت
    -0.68
    IsNotEmpty
    -0.67
    niveau
    -0.67
     corpses
    -0.67
    POSITIVE LOGITS
    worm
    0.74
     Sai
    0.73
     Thursdays
    0.72
     qashqai
    0.71
     Eugène
    0.70
     Acces
    0.70
     Optimization
    0.69
    FIRE
    0.69
     colomb
    0.69
     kei
    0.69
    Activations Density 0.010%

    No Known Activations