© 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. 13789
    Prev
    Next
    INDEX
    Explanations

    Contains architecture, Asia, usage, aliens, core, terminal, streetwear

    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
     주목
    0.91
     кстати
    0.88
     साधना
    0.85
     一个
    0.84
    ^*$
    0.84
     אני
    0.84
     כש
    0.82
    သုံးပြု
    0.82
     عزیز
    0.81
    cles
    0.81
    POSITIVE LOGITS
    Contains
    1.02
     Contains
    0.95
    contains
    0.93
    Includes
    0.92
    ذب
    0.90
     comprised
    0.89
    /−
    0.87
     comprising
    0.87
    includes
    0.87
    dengan
    0.86
    Activations Density 0.279%

    No Known Activations