© 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. 22-GEMMASCOPE-2-RES-16K
    7. 8099
    Prev
    Next
    INDEX
    Explanations

    prompts to tailor further

    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_22_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
     in
    3.39
    ใน
    2.94
     dalam
    2.77
     فى
    2.74
     في
    2.70
     în
    2.65
     trong
    2.64
     в
    2.50
    在
    2.50
    dalam
    2.46
    POSITIVE LOGITS
     നിന്ന്
    1.21
     کې
    1.14
     करिएगा
    1.05
     만큼
    1.05
    ereich
    1.00
     vicinity
    1.00
    amiseks
    0.97
    ďaka
    0.97
     જેટ
    0.95
    োন
    0.95
    Activations Density 0.617%

    No Known Activations