© 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. 47548
    Prev
    Next
    INDEX
    Explanations

    LICENSE, chromosomes, km

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

    software license and legal text in technical documents.

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

    This neuron fires on short domain-specific or technical tokens—such as acronyms, units of measure, license or section keywords, and other jargon markers.

    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
     paragraphe
    -0.88
    potion
    -0.78
    ENEZ
    -0.78
     الرغم
    -0.77
    SECUR
    -0.75
     subsets
    -0.75
    zional
    -0.73
     zou
    -0.72
     koe
    -0.71
    AVIA
    -0.71
    POSITIVE LOGITS
    towe
    0.84
     führten
    0.82
    mektedir
    0.77
     passionately
    0.76
    kur
    0.76
     visibilité
    0.75
    ENV
    0.74
    Lato
    0.73
    endregion
    0.73
    instein
    0.73
    Activations Density 0.008%

    No Known Activations