© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 15037
    Prev
    Next
    INDEX
    Explanations

    critical for

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

    This neuron specifically picks out numeric tokens that include 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
     하지만
    0.61
     Киє
    0.59
     Также
    0.59
     然後
    0.59
     Inoltre
    0.58
    콩
    0.56
     Disabled
    0.55
     Watercolor
    0.55
    Elephant
    0.55
    佺
    0.55
    POSITIVE LOGITS
    ばかり
    0.55
    withstanding
    0.54
    midd
    0.53
     determinado
    0.52
    zony
    0.52
     fend
    0.52
    kii
    0.52
    样的
    0.51
    kati
    0.51
    ...
    0.50
    Activations Density 0.000%

    No Known Activations