© 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. 11983
    Prev
    Next
    INDEX
    Explanations

    programming variable names

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

    The neuron consistently activates on decimal number tokens (floating-point numerals).

    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
    ی
    1.13
    ה
    0.99
    labeled
    0.98
    و
    0.97
    a
    0.92
    o
    0.91
    labelled
    0.88
    interpol
    0.84
    e
    0.84
    га
    0.83
    POSITIVE LOGITS
     osmosis
    0.80
    ﻥ
    0.77
     eyelids
    0.76
     思い
    0.74
    ﻯ
    0.74
     vacancies
    0.73
     つい
    0.73
     隣
    0.72
    ៦
    0.72
     Bởi
    0.72
    Activations Density 0.000%

    No Known Activations