© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 4549
    Prev
    Next
    INDEX
    Explanations

    setting personas or tasks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_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
    +)
    0.97
     ประ
    0.97
     素材
    0.95
    (+)
    0.92
     キャン
    0.91
    -)
    0.90
    物品
    0.89
     ""))
    0.89
    THAN
    0.89
    婚礼
    0.88
    POSITIVE LOGITS
     наде
    1.03
    ッセ
    0.95
     mesmas
    0.95
     toute
    0.92
     toutes
    0.90
    Fala
    0.90
     TeV
    0.88
     moelle
    0.88
     mesma
    0.87
     messengers
    0.87
    Activations Density 0.434%

    No Known Activations