© 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. 66720
    Prev
    Next
    INDEX
    Explanations

    code structure delimiters

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

    The neuron detects numeric literals (tokens made up of digits).

    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
    the
    -1.72
     is
    -1.69
    at
    -1.50
    的
    -1.44
    providedIn
    -1.36
    ----------------
    -1.35
    ors
    -1.34
    ѕ
    -1.34
    ataires
    -1.34
    not
    -1.33
    POSITIVE LOGITS
    ↵
    1.67
    割と
    1.45
     absorción
    1.45
    凄く
    1.43
     transición
    1.41
    ホント
    1.41
    誰が
    1.41
    すっ
    1.40
     samoz
    1.39
     they
    1.38
    Activations Density 0.001%

    No Known Activations