© 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
    2. Gemma-3-1B
    3. 13-GEMMASCOPE-2-RES-65K
    4. 1646
    Prev
    Next
    INDEX
    Explanations

    on surfaces and locations

    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
    ing
    1.25
    o
    1.13
    ,
    1.05
    ’
    1.02
    a
    1.00
    )
    0.95
    0
    0.95
    :
    0.92
    us
    0.90
    1
    0.89
    POSITIVE LOGITS
     behalf
    2.00
    िक्रमा
    1.81
     základě
    1.47
    slaught
    1.43
     tenter
    1.36
     pretext
    1.35
    此同时
    1.34
     basis
    1.33
     layi
    1.30
     asuntos
    1.29
    Activations Density 1.169%

    No Known Activations