© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 10669
    Prev
    Next
    INDEX
    Explanations

    those who, of, clients

    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_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
    an
    2.04
    anego
    1.29
    ك
    1.28
    ed
    1.22
    어
    1.22
    ВА
    1.20
    ная
    1.19
    ي
    1.19
    /=
    1.18
     dadurch
    1.18
    POSITIVE LOGITS
     pesky
    2.37
    zelfde
    1.94
     darn
    1.65
     who
    1.63
    ل
    1.48
    ுக்கு
    1.48
     kinds
    1.45
    verständlich
    1.44
     closest
    1.44
     aren
    1.42
    Activations Density 0.026%

    No Known Activations