© 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. 4643
    Prev
    Next
    INDEX
    Explanations

    `CONSTANT`, `String`, names, numbers, `item` `text`

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

    This neuron mainly detects multi-digit numeric tokens (long sequences of digits).

    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
    rological
    0.68
    ructive
    0.59
    rologic
    0.58
    architecture
    0.58
    ቛ
    0.57
    īng
    0.55
    ǎn
    0.54
    肐
    0.54
     архитек
    0.53
    Ი
    0.53
    POSITIVE LOGITS
    1
    0.70
    十几
    0.66
     casi
    0.58
    2
    0.57
    9
    0.56
    ;",
    0.56
    4
    0.54
    อื่นๆ
    0.53
    !,
    0.52
    8
    0.51
    Activations Density 0.003%

    No Known Activations