© 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. 109128
    Prev
    Next
    INDEX
    Explanations

    ureteropelvic junction obstruction

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

    medical and urological terminology related to the urinary tract.

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

    The neuron strongly activates on long, specialized multi‐syllable tokens—i.e. domain-specific technical or jargon terms.

    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
     Football
    -0.88
    Football
    -0.83
    [][
    -0.77
    })).
    -0.76
    strstr
    -0.75
    ISOString
    -0.74
    football
    -0.74
    SqlCommand
    -0.73
    ੋ
    -0.72
     football
    -0.71
    POSITIVE LOGITS
     ureter
    1.24
     ура
    0.80
     Kilkenny
    0.76
    惺
    0.75
     botanique
    0.74
     urine
    0.73
    ilier
    0.73
    Newport
    0.71
    PHS
    0.71
     perist
    0.70
    Activations Density 0.063%

    No Known Activations