© 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. 5511
    Prev
    Next
    INDEX
    Explanations

    true or real nature

    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
    吖
    1.09
     Grower
    1.06
     பதிவு
    1.06
     уважа
    1.05
     Distress
    1.03
     glau
    1.02
     Drought
    0.99
     automaticamente
    0.98
     Boom
    0.98
     ट्रा
    0.98
    POSITIVE LOGITS
    세
    0.85
     sexuality
    0.81
    르
    0.81
     exact
    0.80
     facts
    0.79
     precies
    0.77
    세를
    0.77
     koş
    0.76
    Ĝ
    0.76
    ită
    0.75
    Activations Density 0.160%

    No Known Activations