© 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. 11124
    Prev
    Next
    INDEX
    Explanations

    programming worksheet assignment

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

    The neuron is simply acting as a “position counter,” firing most strongly on tokens that occur around the middle of the document (roughly the 350–400th token).

    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
    ग्र
    0.97
    ص
    0.88
    m
    0.88
    p
    0.84
    s
    0.82
    n
    0.78
     घ्यावी
    0.78
    AIN
    0.76
    yad
    0.75
    t
    0.75
    POSITIVE LOGITS
     Saccharomyces
    0.84
     vrouw
    0.76
     Lots
    0.73
     Justicia
    0.73
     Bestellung
    0.73
     Therapeut
    0.72
     umfass
    0.71
     длиной
    0.71
    ศ์
    0.71
     längst
    0.71
    Activations Density 0.000%

    No Known Activations