© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 4276
    Prev
    Next
    INDEX
    Explanations

    code structure or formatting

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

    The neuron strongly activates on content‐bearing words (nouns, verbs, adjectives) rather than on 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
     thẻ
    0.71
    говори
    0.68
    _<
    0.68
    ča
    0.67
    ètes
    0.67
     Hệ
    0.67
     systèmes
    0.67
    ního
    0.65
     Mỹ
    0.64
     português
    0.64
    POSITIVE LOGITS
    ﺸ
    0.81
     இருப்பினும்
    0.78
    もし
    0.75
    Alright
    0.75
     людьми
    0.75
     piens
    0.75
    したら
    0.73
     रिपीट
    0.71
     детьми
    0.70
    โดย
    0.70
    Activations Density 0.000%

    No Known Activations