© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 6488
    Prev
    Next
    INDEX
    Explanations

    veniam, numbers, anni

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

    The neuron fires on non‐ASCII byte sequences or garbled/multibyte Unicode characters in the text.

    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
     BECAUSE
    0.12
     preguntó
    0.12
    ל
    0.11
    이라는
    0.11
     comenzaron
    0.11
     اين
    0.11
     тази
    0.11
     chrét
    0.10
     inasmuch
    0.10
     গত
    0.10
    POSITIVE LOGITS
     floppy
    0.12
     Lemmas
    0.11
     Hobbit
    0.11
     foreach
    0.11
    ดวก
    0.11
     Encore
    0.11
    $">
    0.11
     ModInt
    0.10
     Flamengo
    0.10
     Drinfeld
    0.10
    Activations Density 0.001%

    No Known Activations