© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 112569
    Prev
    Next
    INDEX
    Explanations

    wy... or BeginInit

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

    The neuron detects occurrences of the letter sequence “Wy” (as in names like “Wycombe,” “Wynette,” etc.).

    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
    龵
    -2.92
    龶
    -2.72
    両方
    -2.58
    er
    -2.39
     crucero
    -2.36
    使い方
    -2.30
    which
    -2.30
    ↵
    -2.28
     urges
    -2.27
    衚
    -2.25
    POSITIVE LOGITS
     willpower
    2.53
    鴞
    2.36
    AutoresizingMask
    2.33
     })
    
    2.31
    ⅓
    2.30
    سانی
    2.27
    鎳
    2.27
    ⇘
    2.20
     }),
    2.19
    ợn
    2.17
    Activations Density 0.001%

    No Known Activations