© 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-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 8133
    Prev
    Next
    INDEX
    Explanations

    file handling and code syntax

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

    This neuron detects numeric tokens that include a decimal point (i.e. floating-point numbers).

    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
    ാ
    0.91
    ة
    0.83
     SwitchCompat
    0.81
     XLSX
    0.80
    Ǎ
    0.80
    Instruction
    0.79
    க்கத்தில்
    0.79
    ⿵
    0.79
    ListArr
    0.79
    CSV
    0.78
    POSITIVE LOGITS
    रात
    0.75
     energized
    0.74
    ifies
    0.70
    也将
    0.69
    iera
    0.68
     garante
    0.67
     alguns
    0.67
     algumas
    0.67
     characterizes
    0.67
     ades
    0.67
    Activations Density 0.000%

    No Known Activations