© 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. 229563
    Prev
    Next
    INDEX
    Explanations

    common phrases

    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
    ntity
    0.50
     মোত
    0.50
    堷
    0.50
    baş
    0.49
    ގައި
    0.49
    poor
    0.49
     במהלך
    0.49
     प्रार
    0.48
    strange
    0.48
     ראש
    0.48
    POSITIVE LOGITS
     Eds
    0.47
     cylinders
    0.45
     stadiums
    0.45
     pavilions
    0.45
     hikes
    0.44
    0
    0.44
     montagnes
    0.43
    ,
    0.43
     rotations
    0.42
     sponges
    0.41
    Activations Density 0.001%

    No Known Activations