© 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-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 667
    Prev
    Next
    INDEX
    Explanations

    destination or direction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post_all/layer_41_width_262k_l0_big
    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
    DataItem
    0.48
     suitability
    0.44
    និច
    0.44
     collision
    0.42
     склада
    0.42
    ائط
    0.41
    加以
    0.41
    Ỡ
    0.41
    configuration
    0.41
    ុម
    0.41
    POSITIVE LOGITS
    前往
    1.33
     pergi
    1.21
     went
    1.16
     visit
    1.11
    goto
    1.09
     Went
    1.09
     goes
    1.08
     goto
    1.06
     travelled
    1.04
     traveled
    1.03
    Activations Density 0.003%

    No Known Activations