© 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. 44183
    Prev
    Next
    INDEX
    Explanations

    words starting with Bra

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

    The neuron fires on tokens containing the sequence “bra,” i.e. words or morphemes that include “bra” (often as a prefix).

    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
    锇
    -3.02
    鹮
    -2.70
    囖
    -2.59
    贽
    -2.55
     If
    -2.55
     mohou
    -2.52
    存于
    -2.48
    赁
    -2.44
     Their
    -2.42
     není
    -2.42
    POSITIVE LOGITS
    a
    4.09
    1
    3.72
    3
    3.22
    2
    3.05
    ౫
    2.94
    0
    2.91
    ा
    2.88
    ?
    2.84
    4
    2.80
    ".
    2.75
    Activations Density 0.018%

    No Known Activations