© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-16K
    7. 2799
    Prev
    Next
    INDEX
    Explanations

    knowledge and sorting

    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
    Negative Logits
    ु
    4.85
    л
    3.99
    ر
    3.71
    ும்
    3.50
    ли
    3.37
    ो
    3.33
     overwhelming
    3.06
    ே
    3.06
    𝜃
    3.05
    د
    3.02
    POSITIVE LOGITS
    时候
    3.27
    ऽ
    3.10
    ۥ
    3.04
    ார்
    2.93
     üks
    2.84
    aneous
    2.82
    ٔ
    2.81
    𝐫
    2.78
    lle
    2.69
    ggio
    2.69
    Activations Density 0.350%

    No Known Activations