© 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. 1036
    Prev
    Next
    INDEX
    Explanations

    acronyms and abbreviations

    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
    ,
    1.16
     m
    1.06
     ins
    1.03
    )
    0.97
     re
    0.96
     be
    0.95
    .
    0.94
    0.93
     in
    0.93
    nder
    0.90
    POSITIVE LOGITS
    itipi
    1.74
    akkhati
    1.62
     afirmou
    1.57
     vibhav
    1.57
    efeu
    1.56
    荼
    1.55
    zerű
    1.54
    ރު
    1.54
    婇
    1.53
    rothed
    1.53
    Activations Density 0.025%

    No Known Activations