© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 1083
    Prev
    Next
    INDEX
    Explanations

    numbered section titles

    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_16k_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
    дің
    2.23
    वानिव
    2.09
    
    2.08
     enfrent
    2.08
    
    2.00
    ન્ટ
    1.95
     gustó
    1.94
    üglich
    1.93
    㐬
    1.91
    
    1.91
    POSITIVE LOGITS
    s
    2.28
    tables
    2.13
    i
    1.90
    u
    1.89
    ோ
    1.89
    ی
    1.87
     herum
    1.84
    ம்
    1.83
    에
    1.82
    as
    1.81
    Activations Density 0.853%

    No Known Activations