© 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. 34-GEMMASCOPE-RES-131K
    7. 77545
    Prev
    Next
    INDEX
    Explanations

    implant surface features

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

    dental and medical implant-related terminology.

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

    The neuron fires on numeric expressions—digits, measurements, counts, percentages, years, and similar number-based tokens.

    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
     Kati
    -0.82
     Baños
    -0.82
    InputGroup
    -0.77
     Substitution
    -0.76
     Epif
    -0.76
    🍜
    -0.73
    anka
    -0.73
    éras
    -0.73
    ندق
    -0.72
     romantis
    -0.72
    POSITIVE LOGITS
     threads
    0.94
     platform
    0.88
     thread
    0.83
    četně
    0.79
     Fanning
    0.78
    Speedy
    0.75
     Schrauben
    0.75
     loading
    0.75
     implant
    0.74
     Platform
    0.74
    Activations Density 0.097%

    No Known Activations