© 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. 28241
    Prev
    Next
    INDEX
    Explanations

    symbols and code

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

    The neuron selectively activates on standalone numeric tokens (i.e. sequences 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
    ären
    -0.81
    Hozzáférés
    -0.77
     empe
    -0.73
    Một
    -0.73
    ﾘ
    -0.72
    ཀ
    -0.71
     кри
    -0.69
     repe
    -0.69
    gettext
    -0.68
    ۗ
    -0.68
    POSITIVE LOGITS
     الجسم
    0.83
     famí
    0.82
     tärke
    0.82
     contrasted
    0.81
    attaque
    0.80
    LECT
    0.79
     zdarma
    0.77
    bicara
    0.75
     adaptar
    0.75
     ubica
    0.75
    Activations Density 0.051%

    No Known Activations