© 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. 84441
    Prev
    Next
    INDEX
    Explanations

    witness

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

    The neuron is detecting the word “witness” (and its plural “witnesses”).

    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
    3
    -3.05
    1
    -2.67
    4
    -2.36
    2
    -2.34
    (
    -2.28
    5
    -2.19
     rampant
    -2.14
    9
    -2.13
    6
    -2.11
    7
    -2.09
    POSITIVE LOGITS
    嗞
    2.81
    檮
    2.81
    medriver
    2.38
    鈈
    2.36
    cologist
    2.36
    ⮜
    2.34
    titial
    2.33
     causado
    2.31
    狆
    2.30
    躂
    2.30
    Activations Density 0.004%

    No Known Activations