© 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. 10779
    Prev
    Next
    INDEX
    Explanations

    item parameters

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

    The neuron fires strongly on marketing‐style superlatives and promotional buzzwords in titles (e.g. “best,” “latest,” “special,” “for you,” 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
    s
    0.90
     neighbors
    0.81
    h
    0.76
    𝒔
    0.76
     neighbor
    0.75
    ы
    0.74
     wod
    0.74
    টাকে
    0.73
     favorite
    0.72
    仨
    0.72
    POSITIVE LOGITS
    enregistrement
    0.74
    azgo
    0.72
    ovna
    0.70
     Nunes
    0.70
    örn
    0.70
     przeb
    0.70
     Federico
    0.68
     duyệt
    0.68
    ாகும்
    0.67
    究
    0.67
    Activations Density 0.000%

    No Known Activations