© 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. 2655
    Prev
    Next
    INDEX
    Explanations

    evocative imagery

    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
    Contracts
    1.15
    เกิน
    1.11
     commitments
    1.10
     quotas
    1.09
     కమి
    1.08
    COMMIT
    1.07
     Worse
    1.07
    >(
    1.04
     surpluses
    1.03
     obliga
    1.03
    POSITIVE LOGITS
     dekor
    2.26
     adorable
    2.19
    图案
    2.09
     colorful
    2.09
     decorative
    2.07
    可愛
    2.05
     elegant
    2.02
     زیبا
    1.98
     Elegant
    1.97
     Colorful
    1.96
    Activations Density 1.308%

    No Known Activations