© 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. 58619
    Prev
    Next
    INDEX
    Explanations

    gab or gabby variants

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

    The neuron activates on any token containing the letter sequence “gab” (in any casing).

    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
     และ
    -2.86
    𓇼
    -2.69
    蚡
    -2.66
     логоти
    -2.59
    
    -2.52
     encontre
    -2.50
    麈
    -2.50
    を使用した
    -2.42
    柺
    -2.39
    珎
    -2.39
    POSITIVE LOGITS
    Following
    2.55
    Only
    2.53
    To
    2.47
    :
    2.36
    For
    2.34
    Surprisingly
    2.33
    In
    2.31
     breathless
    2.30
    Nearly
    2.30
    Before
    2.30
    Activations Density 0.002%

    No Known Activations