© 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. 7372
    Prev
    Next
    INDEX
    Explanations

    scent, flavor, and sensory modifiers

    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
     fixation
    1.02
    §
    0.99
     barbed
    0.91
    روع
    0.89
    电器
    0.89
    езд
    0.87
    সর
    0.86
     ஒழு
    0.86
    大法
    0.85
     ಸಾವಿರ
    0.84
    POSITIVE LOGITS
     кок
    1.02
    焙
    1.00
     McCorm
    0.99
     creamy
    0.98
     Nicki
    0.98
     milder
    0.98
     Valentina
    0.97
     Trey
    0.97
    Tony
    0.96
    Michele
    0.95
    Activations Density 0.389%

    No Known Activations