© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 12568
    Prev
    Next
    INDEX
    Explanations

    surgical approaches

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

    terms related to medical/clinical procedures or biological materials.

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

    The neuron fires on numeric measurement tokens—especially decimal‐formatted numbers (e.g. “125.5”, “24.625”, “110.5”).

    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
     حتی
    -1.20
     även
    -1.15
    的同时
    -1.06
     ciudadanos
    -1.05
     anche
    -1.03
     so
    -1.02
    不仅
    -1.00
    े
    -0.99
     reisen
    -0.99
    也要
    -0.98
    POSITIVE LOGITS
     found
    1.09
    𓂃
    1.05
    有人
    0.98
    但
    0.98
     znovu
    0.98
    而是
    0.96
     verwacht
    0.96
     fusca
    0.95
    ERMIN
    0.95
    filé
    0.95
    Activations Density 0.267%

    No Known Activations