© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 42317
    Prev
    Next
    INDEX
    Explanations

    shy or yaw rotation

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

    The neuron consistently fires on occurrences of the substring “shy” (in any casing or context).

    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
    ஂ
    -2.92
     Not
    -2.84
    剮
    -2.64
    哢
    -2.59
     investiga
    -2.53
     obliga
    -2.41
    祆
    -2.41
     observa
    -2.41
    ꦠ
    -2.38
    
    -2.36
    POSITIVE LOGITS
    out
    2.84
    𞤢
    2.78
    [
    2.48
     totalement
    2.45
    𐬹
    2.39
     allemand
    2.33
    faced
    2.19
     même
    2.17
    abaikan
    2.17
    where
    2.16
    Activations Density 0.001%

    No Known Activations