© 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-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 5665
    Prev
    Next
    INDEX
    Explanations

    Node.js and JavaScript

    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_22_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
    .
    0.56
    фикация
    0.54
    。【
    0.53
     ሕ
    0.53
    (...
    0.52
    ।
    0.52
    क्ट
    0.51
     đều
    0.51
     manc
    0.51
     áng
    0.50
    POSITIVE LOGITS
    AD
    0.95
     Takes
    0.93
    NET
    0.91
     Minus
    0.89
    Cs
    0.89
    А
    0.89
     Taking
    0.89
    𝐀
    0.88
     Some
    0.88
    A
    0.87
    Activations Density 0.054%

    No Known Activations