© 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. 244
    Prev
    Next
    INDEX
    Explanations

    website domains

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

    The neuron fires most strongly on numeric values that include decimal points (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
    tas
    0.31
    tos
    0.30
     Canva
    0.28
    t
    0.28
     improbable
    0.27
     possessions
    0.26
     RMSE
    0.26
     infuse
    0.26
     Hades
    0.26
    tie
    0.25
    POSITIVE LOGITS
    ığı
    0.28
    jpg
    0.27
    рд
    0.26
    潘
    0.26
    unnumbered
    0.26
    ם
    0.26
    iguë
    0.26
    ᐟ
    0.26
     Букмекер
    0.25
    ันทร์
    0.25
    Activations Density 0.541%

    No Known Activations