© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 12049
    Prev
    Next
    INDEX
    Explanations

    ordering and induced

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

    The neuron primarily activates on floating-point numeric tokens (i.e. numbers containing a decimal point).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ﺭ
    0.79
    лые
    0.78
    eden
    0.77
     bonito
    0.75
    うまく
    0.74
    }||
    0.73
     misalignment
    0.73
     erk
    0.73
    Mis
    0.72
     Grün
    0.71
    POSITIVE LOGITS
    т
    0.88
    ت
    0.82
    นิ
    0.81
     piloted
    0.78
     predicate
    0.77
    น
    0.77
    м
    0.76
    ection
    0.76
     項
    0.73
     vérité
    0.73
    Activations Density 0.000%

    No Known Activations