© 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. 13-GEMMASCOPE-2-RES-16K
    7. 13856
    Prev
    Next
    INDEX
    Explanations

    data source and space

    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
    >');
    1.95
    moderate
    1.94
    اطع
    1.94
    ловать
    1.92
    ᐟ
    1.88
    تش
    1.86
    wellery
    1.86
    नेटिक
    1.84
    俬
    1.83
    embr
    1.83
    POSITIVE LOGITS
     "<<
    2.14
     Placing
    2.07
     Oni
    2.05
     "...
    2.03
     $"
    1.95
     Fast
    1.92
    ের
    1.91
    ぇ
    1.91
    বধূ
    1.91
    䜣
    1.91
    Activations Density 0.008%

    No Known Activations