© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 19658
    Prev
    Next
    INDEX
    Explanations

    code strings and assignments

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

    The neuron flags any token containing one or more digits (i.e. numeric literals or strings with 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_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
    ITAN
    -1.96
    缓缓
    -1.93
    Дере
    -1.75
    —”
    -1.69
     TAMBÉM
    -1.66
    瘆
    -1.62
    Уже
    -1.62
    และ
    -1.61
    albeit
    -1.61
    й
    -1.60
    POSITIVE LOGITS
    0
    1.71
    ↵
    1.63
     Those
    1.53
     Nachfolger
    1.49
     attempting
    1.48
     lettore
    1.45
     in
    1.43
     tentativo
    1.41
     those
    1.39
     using
    1.38
    Activations Density 0.051%

    No Known Activations