© 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. 7703
    Prev
    Next
    INDEX
    Explanations

    numbers and specific characters

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

    The neuron does not activate on any tokens—it never finds anything.

    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
     c
    0.51
    CO
    0.51
     ৪৫
    0.50
    Hace
    0.48
    I
    0.48
    5
    0.48
     cách
    0.47
    Vic
    0.47
    C
    0.47
     CO
    0.47
    POSITIVE LOGITS
     अभिनेत्री
    0.58
     автофо
    0.54
     ćel
    0.54
    𝗮
    0.54
     অভিনেত্র
    0.52
     microphones
    0.51
     broadcasters
    0.50
    িয়ার
    0.50
     grabación
    0.50
     micrófono
    0.49
    Activations Density 0.018%

    No Known Activations