© 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. 4891
    Prev
    Next
    INDEX
    Explanations

    explaining why something is important

    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
    u
    0.57
    6
    0.56
    T
    0.56
    fecha
    0.55
    state
    0.53
     fantástico
    0.53
    l
    0.52
    time
    0.52
    re
    0.51
    K
    0.50
    POSITIVE LOGITS
    这么多
    0.62
     этом
    0.60
    াতের
    0.57
     this
    0.56
     estern
    0.55
     endeavour
    0.54
     questo
    0.53
     endeavor
    0.52
    那么多
    0.52
     இந்த
    0.52
    Activations Density 0.761%

    No Known Activations