© 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-262K
    7. 12289
    Prev
    Next
    INDEX
    Explanations

    extracting words or information

    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_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ر
    3.05
     hunch
    2.92
     else
    2.71
    न
    2.53
    рования
    2.53
    lere
    2.53
     awalnya
    2.48
     Weitere
    2.47
     fh
    2.46
     nCmdShow
    2.44
    POSITIVE LOGITS
    ا
    4.13
    tion
    3.34
     Перейти
    3.18
    stoffe
    2.93
    tiden
    2.93
    на
    2.87
    tips
    2.81
     terrest
    2.75
     kren
    2.71
    torrent
    2.69
    Activations Density 0.053%

    No Known Activations