© 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. 200190
    Prev
    Next
    INDEX
    Explanations

    fulfill one

    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
     prescriptive
    0.54
    or
    0.52
    d
    0.47
    DX
    0.45
    baked
    0.45
    nikov
    0.44
     निजा
    0.44
    ethash
    0.43
    y
    0.43
    variety
    0.42
    POSITIVE LOGITS
     viaggio
    0.50
    舰
    0.48
    ᱧ
    0.48
     resumen
    0.47
    ႅ
    0.47
     marchio
    0.46
     apoyo
    0.46
     término
    0.46
     setTo
    0.46
     apoio
    0.44
    Activations Density 0.001%

    No Known Activations