© 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. 2821
    Prev
    Next
    INDEX
    Explanations

    Animal God Orange Pink

    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
     আক্রম
    1.23
    
    1.10
    жения
    1.07
    也要
    1.06
    させて頂
    1.05
    させていただ
    1.02
    melidir
    1.02
    期的
    1.02
     затруд
    1.01
    Should
    1.01
    POSITIVE LOGITS
     גי
    1.00
     ges
    0.97
     discover
    0.96
    ₫
    0.93
     GIFs
    0.93
     Pinterest
    0.90
     Pagination
    0.90
     Tweets
    0.89
     besten
    0.88
     TikTok
    0.88
    Activations Density 0.877%

    No Known Activations