© 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. 29-GEMMASCOPE-2-RES-262K
    7. 147153
    Prev
    Next
    INDEX
    Explanations

    help lines and numbers

    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_29_width_262k_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
     cartridges
    0.80
    Keefe
    0.78
    ฮ
    0.77
     cartridge
    0.75
     निजा
    0.75
     Cart
    0.74
     cantidades
    0.74
     Tiles
    0.73
     Rodgers
    0.73
    <unused425>
    0.73
    POSITIVE LOGITS
     সরকারী
    0.63
     ხელისუფლების
    0.61
     গভীর
    0.60
     Север
    0.60
     deep
    0.59
    后端
    0.58
    ,…
    0.57
     شکل
    0.57
    netHex
    0.56
     глубо
    0.55
    Activations Density 0.003%

    No Known Activations