© 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. 2185
    Prev
    Next
    INDEX
    Explanations

    word endings

    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
    a
    5.09
    ي
    5.07
    ০
    4.73
    an
    4.69
    ில்
    4.62
    iť
    4.54
    ת
    4.52
    л
    4.51
    ம்
    4.50
    i
    4.44
    POSITIVE LOGITS
    tttt
    4.53
    ting
    4.52
    ttt
    4.12
    ty
    3.95
    tainment
    3.78
    tt
    3.73
    መሳሳይ
    3.53
    न्त्र
    3.51
    tted
    3.48
    ted
    3.37
    Activations Density 0.957%

    No Known Activations