© 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. 11053
    Prev
    Next
    INDEX
    Explanations

    portion of variants

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

    The neuron flags unusually rare or infrequent words (i.e. low‐frequency tokens).

    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
     rozwią
    0.79
    ₦
    0.77
     szolg
    0.76
     đổi
    0.74
     libero
    0.70
     επισ
    0.68
     patrón
    0.68
     απε
    0.68
     terapé
    0.67
    withId
    0.67
    POSITIVE LOGITS
    ي
    0.94
    й
    0.86
    ी
    0.86
    ваме
    0.83
    нд
    0.82
    цем
    0.80
    er
    0.79
    гти
    0.78
    يلا
    0.78
    ીર
    0.76
    Activations Density 0.000%

    No Known Activations