© 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. 17-GEMMASCOPE-2-RES-16K
    7. 3557
    Prev
    Next
    INDEX
    Explanations

    my purpose is to be helpful and harmless

    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_17_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
    ज
    0.71
    øy
    0.71
    ü
    0.69
     मानदंडों
    0.69
    sorted
    0.66
     எடுத்து
    0.66
    Cycl
    0.64
     criteria
    0.64
     calendar
    0.64
    平成
    0.63
    POSITIVE LOGITS
     отказыва
    0.74
     সংস্থা
    0.71
    aprendizaje
    0.71
     dụ
    0.70
     моби
    0.70
    叮
    0.69
    囑
    0.69
     pemberian
    0.68
     forests
    0.68
     maa
    0.68
    Activations Density 0.087%

    No Known Activations