© 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. 146766
    Prev
    Next
    INDEX
    Explanations

    personal ambition

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

    active object manipulation

    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
     effectual
    0.52
    \
    0.47
    мани
    0.45
    се
    0.43
    ிலோ
    0.43
     despair
    0.42
     preconceived
    0.42
     or
    0.41
     ނ
    0.41
    filePath
    0.40
    POSITIVE LOGITS
     moyennes
    0.50
     ASSEM
    0.48
     Spectroscopy
    0.46
    LAT
    0.45
     Continuity
    0.45
    WAT
    0.45
     素
    0.44
     stejně
    0.43
    ²',
    0.43
     घुल
    0.42
    Activations Density 0.001%

    No Known Activations