© 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. 2169
    Prev
    Next
    INDEX
    Explanations

    creative applications and choices

    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
    т
    5.37
    t
    4.29
    ر
    3.78
    ers
    3.73
    r
    3.68
    ق
    3.62
    ের
    3.60
    nya
    3.49
    са
    3.40
    st
    3.37
    POSITIVE LOGITS
     menge
    3.12
    ReferencePose
    3.10
    겐
    3.04
    класс
    2.78
    деся
    2.74
     stir
    2.70
    StringVar
    2.70
     voce
    2.68
    ٔ
    2.67
    𝗜
    2.66
    Activations Density 0.447%

    No Known Activations