© 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. 13014
    Prev
    Next
    INDEX
    Explanations

    first confirmed

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

    The neuron flags “content‐bearing” words – especially proper names, titles, and other semantically important nouns.

    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
    {
    0.77
    ?!?
    0.75
    Ско
    0.75
     deleterious
    0.73
    ER
    0.73
    :
    0.72
    榞
    0.71
    \
    0.68
    O
    0.67
    prime
    0.66
    POSITIVE LOGITS
    女
    0.90
     жена
    0.89
     tamaño
    0.89
     жен
    0.88
     лі
    0.86
    스럽
    0.85
     promesa
    0.85
     idempot
    0.84
     ligeramente
    0.84
     femenino
    0.84
    Activations Density 0.000%

    No Known Activations