© 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. 4404
    Prev
    Next
    INDEX
    Explanations

    german or english words

    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
    inventory
    0.99
    郵便
    0.95
    주의
    0.95
    izing
    0.95
     Notice
    0.94
    CHA
    0.93
     Schedules
    0.93
    :.
    0.93
    Notice
    0.93
    notice
    0.93
    POSITIVE LOGITS
     tenho
    1.06
     ediyor
    1.04
     uop
    1.01
     eddies
    1.01
    kách
    1.01
     फ्लावर
    1.00
    Fps
    0.99
    rik
    0.97
     plataforma
    0.97
    squiggle
    0.97
    Activations Density 0.002%

    No Known Activations