© 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. 13733
    Prev
    Next
    INDEX
    Explanations

    writing and

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

    The neuron flags semantically important “content” words (key nouns, verbs, or adjectives) and ignores common function words.

    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
    ლებიც
    0.87
     lulus
    0.86
    ى
    0.86
     assuring
    0.85
     indefinitely
    0.83
    ٹنگ
    0.81
    ولوج
    0.79
     chores
    0.79
    ফর্ম
    0.79
    اموش
    0.79
    POSITIVE LOGITS
    اص
    0.80
    e
    0.78
    ENTE
    0.77
    aan
    0.72
     افواج
    0.70
    accarat
    0.69
     estuv
    0.68
    container
    0.68
    所得
    0.68
    OF
    0.66
    Activations Density 0.000%

    No Known Activations