© 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-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 6191
    Prev
    Next
    INDEX
    Explanations

    using

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-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
    кт
    0.73
     Rough
    0.71
    ht
    0.71
     છ
    0.68
     গেরিলা
    0.66
     tránh
    0.65
     Overseas
    0.65
    hu
    0.64
     paraphrase
    0.64
     прогноз
    0.64
    POSITIVE LOGITS
    有机会
    0.88
     using
    0.86
    蓆
    0.84
     menggunakan
    0.82
     باستخدام
    0.79
     WITH
    0.79
     USING
    0.77
     utilisant
    0.77
     Using
    0.77
    Using
    0.76
    Activations Density 0.430%

    No Known Activations