© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 139941
    Prev
    Next
    INDEX
    Explanations

    ownership rights and personal requests

    np_acts-logits-general · gemini-2.5-flash-lite

    when then conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ר
    0.58
    க்கோ
    0.49
    ח
    0.48
     champ
    0.48
     sired
    0.48
    ℝ
    0.48
    Ach
    0.48
     campeón
    0.48
     was
    0.47
     stric
    0.47
    POSITIVE LOGITS
     अवर
    0.43
    full
    0.43
    endering
    0.42
    o
    0.42
     顔
    0.41
     不同
    0.41
    datetime
    0.41
    mam
    0.41
    ibrated
    0.41
    endon
    0.41
    Activations Density 0.001%

    No Known Activations