© 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. 22-GEMMASCOPE-RES-131K
    7. 27989
    Prev
    Next
    INDEX
    Explanations

    punctuation followed by " I"

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

    The neuron chiefly fires on numeric tokens (numbers and numerical punctuation).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    奬
    -1.24
     toJson
    -1.23
     geweldige
    -1.08
     недорого
    -1.06
     vuitton
    -1.06
     ワイン
    -1.00
     aquest
    -0.99
    喟
    -0.99
     весьма
    -0.98
    ままで
    -0.98
    POSITIVE LOGITS
     I
    1.91
     they
    1.46
    чного
    1.35
    Meskipun
    1.34
    ค่ะ
    1.30
     ogrom
    1.29
    我覺得
    1.28
    CppMethod
    1.21
     kteří
    1.20
     которая
    1.18
    Activations Density 0.017%

    No Known Activations