© 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. 16-GEMMASCOPE-2-RES-262K
    7. 144415
    Prev
    Next
    INDEX
    Explanations

    lattices

    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_16_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
     亠
    0.52
    formes
    0.49
    邳
    0.49
     \|\
    0.47
    squre
    0.47
    ະພັນ
    0.47
     rupam
    0.46
     )\
    0.46
     kammam
    0.46
     Klinefelter
    0.46
    POSITIVE LOGITS
    You
    0.52
    k
    0.50
    át
    0.48
     дли
    0.47
    خ
    0.46
    enso
    0.44
    Mark
    0.43
    Make
    0.41
    ude
    0.41
     stal
    0.41
    Activations Density 0.001%

    No Known Activations