© 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. 31-GEMMASCOPE-2-RES-262K
    7. 9298
    Prev
    Next
    INDEX
    Explanations

    in small batches, individually

    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
    Negative Logits
    禟
    0.49
    狲
    0.45
     活动
    0.44
     wikip
    0.44
     spolupr
    0.43
     sAlarm
    0.43
    InterfaceLine
    0.42
    𒅴
    0.42
     způ
    0.41
     ennemis
    0.41
    POSITIVE LOGITS
     I
    0.58
    I
    0.55
    D
    0.50
    B
    0.49
     B
    0.49
     U
    0.47
     D
    0.47
     and
    0.45
     R
    0.45
    R
    0.44
    Activations Density 0.001%

    No Known Activations