© 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. 85695
    Prev
    Next
    INDEX
    Explanations

    latest setback, still important

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

    offering recipes, options, ideas

    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
     пул
    0.45
    결
    0.45
    Databaze
    0.44
    dispers
    0.44
     фено
    0.44
     stalled
    0.43
    ган
    0.43
    院
    0.42
     изпъл
    0.42
    arsipkan
    0.41
    POSITIVE LOGITS
     seraient
    0.59
     Voici
    0.52
     Familiar
    0.51
     Consider
    0.49
     Base
    0.49
     wären
    0.48
     ['
    0.48
     Interesting
    0.48
     interessant
    0.48
     coisas
    0.48
    Activations Density 0.001%

    No Known Activations