© 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. 15977
    Prev
    Next
    INDEX
    Explanations

    variable names and code structures

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

    The neuron fires on numeric tokens or numeric expressions (e.g. indices, measurements, coordinates, and other number literals).

    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
    🔚
    0.61
     minimalism
    0.59
    ధు
    0.55
     tendencias
    0.55
    designated
    0.55
    Bahn
    0.55
    truncated
    0.55
    textrm
    0.54
    Thou
    0.54
    rothed
    0.54
    POSITIVE LOGITS
     jika
    0.58
     =
    0.57
     Sapphire
    0.56
     இது
    0.55
     หาก
    0.54
     since
    0.54
     यह
    0.54
     Properties
    0.54
     Bundle
    0.54
     এটি
    0.53
    Activations Density 0.000%

    No Known Activations