© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 3709
    Prev
    Next
    INDEX
    Explanations

    advantages and opportunities

    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_7_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
    ுமா
    2.39
    NESS
    2.30
    egrave
    2.30
     breed
    2.24
    ोटा
    2.23
    πηρε
    2.22
    ি
    2.22
    riva
    2.14
    
    2.11
    хал
    2.10
    POSITIVE LOGITS
    ي
    3.32
    y
    3.23
    i
    2.99
    prüsü
    2.94
    точные
    2.90
    en
    2.85
    opropyl
    2.77
    SEVERE
    2.72
     onCreateView
    2.66
    ené
    2.61
    Activations Density 0.301%

    No Known Activations