© 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. 75003
    Prev
    Next
    INDEX
    Explanations

    answer or posted date

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

    This neuron detects answer/post metadata headers (e.g. labels like “回答” or “Posted”).

    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
    ൎ
    -2.56
    ities
    -2.45
    X
    -2.38
    i
    -2.23
    ↵
    -2.13
     inherently
    -2.09
    S
    -1.97
     be
    -1.95
    （※
    -1.94
    D
    -1.94
    POSITIVE LOGITS
    俟
    2.25
     撮り
    2.23
    읖
    2.20
    莖
    2.19
    Ꞓ
    2.16
     unſ
    2.16
    
    2.16
    続け
    2.14
    Ꮿ
    2.11
    說是
    2.05
    Activations Density 0.000%

    No Known Activations