© 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. 7987
    Prev
    Next
    INDEX
    Explanations

    temporary file storage

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

    This neuron fires on unusually specific or low‐frequency content words (e.g. rare proper nouns or uncommon terms).

    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
    ріа
    0.81
     сказа
    0.80
     рі
    0.77
    ເຂ
    0.77
     ş
    0.76
    그리고
    0.76
     baca
    0.71
     열
    0.70
    க்கூ
    0.70
     чолові
    0.70
    POSITIVE LOGITS
     препаратов
    0.85
    َه
    0.85
    )}"
    0.82
    َم
    0.80
     heredit
    0.77
    م
    0.77
    )},\
    0.76
    بار
    0.76
    )^{*
    0.76
    分け
    0.76
    Activations Density 0.000%

    No Known Activations