© 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. 14800
    Prev
    Next
    INDEX
    Explanations

    asking even basic questions

    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
     percent
    1.36
     শতাংশ
    1.34
    %，
    1.33
    ½
    1.30
     whopping
    1.28
    7
    1.26
    %,
    1.26
    ⅔
    1.26
     million
    1.25
    million
    1.24
    POSITIVE LOGITS
    穷
    1.20
    后面的
    1.10
    內容
    1.10
     Тихо
    1.09
    гар
    1.08
    вета
    1.06
     такое
    1.06
    ถูกต้อง
    1.05
     iremos
    1.05
    щик
    1.05
    Activations Density 0.079%

    No Known Activations