© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 112263
    Prev
    Next
    INDEX
    Explanations

    reported to the Pediatric Health Information System

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

    technical text like code snippets, error messages, or data formatted in tables.

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

    The neuron fires on tokens that represent quantitative data—especially decimal‐number entries in tables or scientific/statistical contexts.

    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
     fumo
    -1.56
     eene
    -1.52
     ERSITY
    -1.45
     juf
    -1.44
     mals
    -1.42
     Biblia
    -1.41
     Filosof
    -1.39
     fonde
    -1.38
     robuste
    -1.34
     hals
    -1.34
    POSITIVE LOGITS
     each
    1.61
     with
    1.53
     types
    1.38
     every
    1.35
     Unterhaltung
    1.31
     like
    1.31
     where
    1.27
     начали
    1.27
     before
    1.26
     Every
    1.26
    Activations Density 0.073%

    No Known Activations