© 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. 7408
    Prev
    Next
    INDEX
    Explanations

    technical or code context

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

    The neuron is highly sensitive to numeric tokens (especially multi-digit and decimal 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
     EVERYTHING
    0.82
     EVERY
    0.75
     HUGE
    0.75
     करोड़
    0.74
     THREE
    0.73
     YOU
    0.70
    !!!!
    0.70
     MARKET
    0.70
     FOUR
    0.69
    三大
    0.68
    POSITIVE LOGITS
     yalnızca
    0.69
     nontrivial
    0.68
     nong
    0.68
    っぽい
    0.63
     비슷한
    0.63
     plaintext
    0.63
     unremarkable
    0.63
     vaguely
    0.62
     일반적으로
    0.62
     distinguishable
    0.61
    Activations Density 0.141%

    No Known Activations