© 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. 10996
    Prev
    Next
    INDEX
    Explanations

    legal, married, consulting, diary, predictability

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

    The neuron detects numeric tokens containing 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
    ウント
    0.72
    睢
    0.69
    你
    0.68
    ứng
    0.66
    Ꭴ
    0.66
    बांग
    0.66
    筚
    0.66
    ოტ
    0.66
    ቛ
    0.66
    éto
    0.65
    POSITIVE LOGITS
     дека
    0.84
     determinada
    0.79
    constants
    0.76
     registrado
    0.74
     ребенок
    0.74
     deği
    0.73
    JECT
    0.72
     преде
    0.72
     december
    0.71
    ায়
    0.70
    Activations Density 0.000%

    No Known Activations