© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 86345
    Prev
    Next
    INDEX
    Explanations

    chess pieces and days

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

    The neuron activates strongly on the “p-w-n” sequence (e.g. “pawn,” “pawns,” “PWN”), i.e. tokens containing that trigram.

    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
    3
    -2.86
     \
    -2.73
    -2.58
    ’
    -2.56
    1
    -2.45
     gewiß
    -2.45
    냅
    -2.45
    เกง
    -2.39
    霂
    -2.39
    0
    -2.36
    POSITIVE LOGITS
    ्रीय
    2.61
    刧
    2.59
    ⬮
    2.56
    ﹍﹍
    2.42
    皷
    2.41
    鴫
    2.38
    稹
    2.38
    ৢ
    2.34
    ↵↵
    2.31
    힛
    2.31
    Activations Density 0.005%

    No Known Activations