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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 5260
    Prev
    Next
    INDEX
    Explanations

    cannot and will not provide

    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
    şi
    2.37
    și
    2.23
    UIViewController
    2.15
     unsolicited
    2.04
    ির্ব
    1.98
    ඒ
    1.95
    ০০
    1.91
    CXX
    1.88
    
    1.86
     médiane
    1.85
    POSITIVE LOGITS
    gir
    2.12
    go
    2.12
    습니다
    2.09
    nok
    2.07
    ringing
    2.03
    gar
    1.99
    gte
    1.97
    gol
    1.97
    dan
    1.94
    ّه
    1.93
    Activations Density 0.171%

    No Known Activations