© 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. 10-GEMMASCOPE-RES-131K
    7. 102718
    Prev
    Next
    INDEX
    Explanations

    rodent-borne diseases and oncology research

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

    references to rodents (rats, mice) in scientific or medical contexts.

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

    Neuron 4 detects bracketed alphanumeric identifiers (e.g. codes in square brackets).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    '
    -3.73
    s
    -2.86
    vantaged
    -2.83
        
    -2.75
     estekak
    -2.63
    "
    -2.58
     mengumumkan
    -2.52
    多かった
    -2.44
    馓
    -2.41
    4
    -2.36
    POSITIVE LOGITS
    骓
    2.86
    六年
    2.66
     –
    2.64
    龑
    2.48
    趼
    2.47
    
    2.45
     have
    2.30
     事例
    2.27
    
    2.27
    牒
    2.23
    Activations Density 0.003%

    No Known Activations