© 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. 112688
    Prev
    Next
    INDEX
    Explanations

    robotic systems or catalytic activity

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

    The neuron detects mentions of “robotic” (and its variants like “robotically,” “robotic-assisted,” etc.) in the text.

    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
    ↵↵
    -2.39
    d
    -2.31
    *
    -2.19
    c
    -2.17
     And
    -2.14
    e
    -2.11
    or
    -2.03
    on
    -1.98
    “
    -1.97
     THE
    -1.95
    POSITIVE LOGITS
    沨
    2.89
    寕
    2.58
    تیجه
    2.58
    鵟
    2.42
     Selasa
    2.30
    厯
    2.27
    acterísticas
    2.27
    我没
    2.23
    鲎
    2.23
     bluza
    2.17
    Activations Density 0.009%

    No Known Activations