© 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. 9-GEMMASCOPE-2-RES-16K
    7. 1675
    Prev
    Next
    INDEX
    Explanations

    or and

    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_9_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
    nienie
    1.51
    ╞
    1.46
    donald
    1.39
    sair
    1.38
     dotted
    1.35
     nying
    1.35
    arence
    1.35
    მასრულ
    1.33
    ofthe
    1.33
    sus
    1.32
    POSITIVE LOGITS
     or
    1.72
     или
    1.59
     and
    1.53
     یا
    1.47
     કરવા
    1.34
     и
    1.32
    하거나
    1.31
     stimulate
    1.28
    and
    1.25
     timeouts
    1.25
    Activations Density 1.639%

    No Known Activations