© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-16K
    7. 974
    Prev
    Next
    INDEX
    Explanations

    people who ask, think, care, say

    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
    ه
    4.17
    o
    3.63
    ください
    3.58
    ो
    3.51
    ので
    3.27
    ोम
    3.04
    त
    2.83
    stimulated
    2.81
    म्मीद
    2.71
    ing
    2.70
    POSITIVE LOGITS
    ɖ
    2.53
     payoffs
    2.48
     utterances
    2.46
    ли
    2.34
     smugglers
    2.32
     lysed
    2.31
    ◀
    2.31
    plectic
    2.30
     flanges
    2.29
    литься
    2.26
    Activations Density 0.087%

    No Known Activations