© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 2162
    Prev
    Next
    INDEX
    Explanations

    money, numbers, years

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

    The neuron specializes in picking out numeric tokens with decimal points (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
    ḏ
    0.60
    𝐡
    0.59
    𝐳
    0.59
     abrigo
    0.56
     ankaŭ
    0.55
     đ
    0.54
     oWord
    0.54
     urma
    0.54
     okra
    0.54
     Navigate
    0.54
    POSITIVE LOGITS
    <0x0C>
    0.69
    od
    0.62
    il
    0.59
    og
    0.57
    on
    0.56
    на
    0.56
    uss
    0.56
    2
    0.55
    ats
    0.53
    eval
    0.52
    Activations Density 0.009%

    No Known Activations