© 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. 5142
    Prev
    Next
    INDEX
    Explanations

    think of it as a way

    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
     plus
    0.88
     +
    0.87
    plus
    0.72
    ation
    0.71
    gne
    0.68
    ثة
    0.68
    +
    0.68
    iation
    0.67
    면
    0.67
    ıza
    0.66
    POSITIVE LOGITS
    road
    0.74
     निरीक्षक
    0.71
    __(/*!
    0.67
     Nyl
    0.67
     سەر
    0.67
    ロード
    0.66
    迩
    0.66
     Road
    0.66
    黄色
    0.66
     strada
    0.65
    Activations Density 0.038%

    No Known Activations