© 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. 7864
    Prev
    Next
    INDEX
    Explanations

    key provisionsbiological sexice cream

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

    The neuron is detecting numeric tokens—especially floating-point numbers and related measure or quantity terms (e.g. “374.954”, “376.435”, “miles”).

    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
    ਸ
    1.02
    त
    0.99
    ת
    0.93
    ع
    0.90
    ল
    0.90
    ِي
    0.89
    ल
    0.86
     وق
    0.85
    ställ
    0.85
    l
    0.84
    POSITIVE LOGITS
    UpperCase
    0.80
    PixelRatio
    0.78
    ようだ
    0.75
    怼
    0.74
    Chiều
    0.73
    Millis
    0.72
    नेटरी
    0.72
     computationally
    0.72
     micró
    0.72
    FRAMERATE
    0.72
    Activations Density 0.000%

    No Known Activations