© 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. 5646
    Prev
    Next
    INDEX
    Explanations

    temperatura mínima

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

    The neuron fires exclusively on the standalone word “telecast.”

    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
    деся
    0.90
    м
    0.82
    йде
    0.76
    чают
    0.76
    glTex
    0.76
    asını
    0.75
     Tú
    0.75
    vì
    0.72
     Nez
    0.72
    йт
    0.72
    POSITIVE LOGITS
    ER
    0.89
    OR
    0.80
    CS
    0.79
    OMET
    0.77
    ERICK
    0.75
     月
    0.73
     June
    0.72
     ended
    0.72
    ภัย
    0.72
    ELINE
    0.72
    Activations Density 0.000%

    No Known Activations