© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 2723
    Prev
    Next
    INDEX
    Explanations

    part of or parts of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    relse
    1.15
    imetric
    1.01
    첩
    0.99
    డే
    0.99
     choose
    0.99
    خانه
    0.98
    पैकी
    0.97
     saja
    0.97
    rix
    0.97
    full
    0.95
    POSITIVE LOGITS
     поговорим
    1.20
     мозга
    1.19
    
    1.19
    ̮
    1.15
     Inhalt
    1.14
     hci
    1.14
     Staff
    1.12
    Staff
    1.11
    ه‌
    1.10
    Hardware
    1.10
    Activations Density 1.277%

    No Known Activations