© 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. 31-GEMMASCOPE-2-RES-262K
    7. 3992
    Prev
    Next
    INDEX
    Explanations

    i can do that

    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/layer_31_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
    these
    0.31
     discontinuation
    0.30
    鋐
    0.29
     これらの
    0.28
    这段
    0.28
     theses
    0.28
     Multip
    0.27
    britann
    0.27
     মতোই
    0.26
    Multip
    0.26
    POSITIVE LOGITS
     в
    0.37
     dengan
    0.33
     با
    0.33
     для
    0.32
    dengan
    0.30
     với
    0.30
     самых
    0.30
     със
    0.29
    chini
    0.29
     באמצעות
    0.29
    Activations Density 0.151%

    No Known Activations