© 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. 44210
    Prev
    Next
    INDEX
    Explanations

    general practitioner or genetic programming

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

    abbreviations in parentheses, particularly 'GP' which appears to represent General Practice, General Practitioners, Glycoprotein, or other technical terms.

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

    This neuron is triggered by occurrences of the uppercase letter sequence “GP” (often in technical abbreviations like GP, Gpx, GPCR).

    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
    ᕱ
    -2.95
    皛
    -2.44
    ꜆
    -2.42
    聼
    -2.36
     área
    -2.36
    倂
    -2.31
     caixas
    -2.30
    腧
    -2.30
    出てきた
    -2.27
    呔
    -2.27
    POSITIVE LOGITS
    >
    3.39
    A
    2.97
    k
    2.84
    N
    2.73
    9
    2.69
    If
    2.66
    U
    2.66
    W
    2.64
    V
    2.58
    J
    2.58
    Activations Density 0.008%

    No Known Activations