© 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-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 64434
    Prev
    Next
    INDEX
    Explanations

    moving into or out of places

    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
    Moved
    0.57
     move
    0.57
     moved
    0.57
     transferred
    0.56
     migration
    0.53
     migrated
    0.53
     옮
    0.52
     transfer
    0.52
     이동
    0.51
    转移
    0.51
    POSITIVE LOGITS
     Holloway
    0.42
    দিনের
    0.39
    掊
    0.38
    zir
    0.38
    uzu
    0.37
    zul
    0.37
    البه
    0.37
     Brook
    0.37
    enea
    0.36
    ECs
    0.36
    Activations Density 0.000%

    No Known Activations