© 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. 2607
    Prev
    Next
    INDEX
    Explanations

    first instance of something

    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
    й
    3.01
    
    2.20
     kmeans
    2.13
    ли
    2.10
    ع
    2.09
     afresh
    2.05
    お客
    1.99
    ements
    1.97
    directions
    1.97
    ⧐
    1.87
    POSITIVE LOGITS
    م
    2.47
    bbene
    2.37
    Time
    2.04
    sudo
    1.98
    𝐧
    1.98
    hull
    1.98
    𝐬
    1.92
    𝐞
    1.90
    ER
    1.88
    ्ह
    1.86
    Activations Density 0.050%

    No Known Activations