© 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. 4869
    Prev
    Next
    INDEX
    Explanations

    technological doctor Magnet ray string

    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
    삶
    1.12
    雨
    1.12
    㐰
    1.10
    出来る
    1.09
     পরাজ
    1.09
    様々な
    1.07
    그
    1.07
    徒歩
    1.06
    ociety
    1.05
    umboldt
    1.05
    POSITIVE LOGITS
     positively
    1.19
     Anyway
    1.06
     Altogether
    1.04
     Ampl
    1.01
     wrongly
    1.01
    ודי
    1.00
    ))[
    0.99
     Thing
    0.98
    zą
    0.98
     müs
    0.97
    Activations Density 0.000%

    No Known Activations