© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 50000
    Prev
    Next
    INDEX
    Explanations

    voice note or message

    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
    Negative Logits
    ABAD
    0.57
    ურთი
    0.57
     pued
    0.57
    اریخ
    0.56
     indispensables
    0.55
    orylation
    0.55
    രുവനന്തപുരം
    0.55
    瑗
    0.55
    ADELPHIA
    0.54
    ίου
    0.54
    POSITIVE LOGITS
    to
    0.63
    stack
    0.63
    strong
    0.62
    \
    0.61
    on
    0.59
    t
    0.59
    land
    0.58
    то
    0.58
    um
    0.57
    eng
    0.56
    Activations Density 0.000%

    No Known Activations