© 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. 1686
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    azaki
    1.22
    ioribus
    1.17
    較
    1.09
    bleshooting
    1.08
     flexibly
    1.08
    adapt
    1.07
    érature
    1.05
     relatively
    1.05
    omod
    1.05
    cultures
    1.05
    POSITIVE LOGITS
     egot
    1.16
    必须要
    1.14
     inescap
    1.13
     絶対
    1.11
     inev
    1.09
    怒
    1.08
     scream
    1.06
     keinginan
    1.05
     MUST
    1.03
     хочется
    1.02
    Activations Density 1.494%

    No Known Activations