© 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. 16272
    Prev
    Next
    INDEX
    Explanations

    country, company, organization, platform

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

    The neuron strongly activates on numeric tokens (especially multi-digit numbers and decimal numbers), i.e. it’s looking for occurrences of 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
    member
    0.73
    -
    0.73
    anesulfonyl
    0.68
    腾
    0.67
     effectu
    0.64
    motors
    0.64
    EM
    0.64
     selaku
    0.63
    mills
    0.62
     également
    0.62
    POSITIVE LOGITS
    ৩৪
    0.89
    ৪৩
    0.87
    TextStyle
    0.86
    achtet
    0.80
    Aslamualaikum
    0.79
     Closeup
    0.78
     அவரின்
    0.77
    𝗠
    0.77
    udades
    0.77
     तरह
    0.77
    Activations Density 0.001%

    No Known Activations