© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-65K
    7. 974
    Prev
    Next
    INDEX
    Explanations

    measurement, validation, quantity

    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_65k_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
    ](
    1.72
    izont
    1.71
    HDL
    1.70
     (’
    1.68
    (--
    1.68
    ,(
    1.64
     границы
    1.64
    첩
    1.64
    éor
    1.63
    chance
    1.63
    POSITIVE LOGITS
     말미암
    1.09
     confond
    1.04
    و
    1.01
    ്യ
    1.00
     Programm
    1.00
    须
    0.99
     맞춰
    0.98
    หน
    0.98
    هو
    0.96
    ק
    0.95
    Activations Density 0.000%

    No Known Activations