© 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. 10853
    Prev
    Next
    INDEX
    Explanations

    SQL queries with JOIN FROM

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

    This neuron tends to fire on mid‐frequency content tokens—i.e. ordinary words that carry substantive meaning rather than very common function words or extremely rare terms.

    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
    sehen
    0.77
     grava
    0.76
    ulfanyl
    0.74
    ర్
    0.73
     `=`,
    0.73
     anaemia
    0.73
     sulfide
    0.71
     dolomite
    0.71
     ампли
    0.70
     учет
    0.70
    POSITIVE LOGITS
    กิจ
    0.92
    らう
    0.79
    leman
    0.77
    らった
    0.73
    and
    0.73
    はお
    0.73
     won
    0.73
    o
    0.71
    ۔
    0.71
     acknowledged
    0.70
    Activations Density 0.000%

    No Known Activations