© 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. 7319
    Prev
    Next
    INDEX
    Explanations

    it can revert

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

    The neuron fires on marketing‐style feature/descriptive phrases in product descriptions (e.g. “arrives ready to hang,” “This direct photographic print,” “Bring your artwork to life,” “To protect our photo art,” etc.).

    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
     ends
    0.67
     endings
    0.65
    ў
    0.65
     zooms
    0.63
    之为
    0.63
     or
    0.63
     storyline
    0.62
    截图
    0.60
     fundament
    0.60
     weathered
    0.60
    POSITIVE LOGITS
     ใหม่
    0.84
     했
    0.76
     व्हाट
    0.76
     미국의
    0.76
     Мини
    0.75
     Sản
    0.75
     Veterinary
    0.74
    bersihan
    0.74
     Сто
    0.73
     नए
    0.73
    Activations Density 0.000%

    No Known Activations