© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 100299
    Prev
    Next
    INDEX
    Explanations

    biological mediators

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

    The neuron detects scientific terms related to biological mediators, particularly in medical and biochemical contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     для
    -2.48
     warmen
    -2.38
     blaue
    -2.36
     帅气
    -2.34
    婠
    -2.31
     Gegensatz
    -2.28
     zwanzig
    -2.28
    镔
    -2.27
    :
    -2.23
     новые
    -2.19
    POSITIVE LOGITS
    </strong>
    3.05
    鴬
    2.97
     However
    2.72
    鬭
    2.70
    ay
    2.63
    跸
    2.41
    y
    2.36
    镡
    2.33
    栳
    2.31
    :";
    2.23
    Activations Density 0.002%

    No Known Activations