© 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. 216006
    Prev
    Next
    INDEX
    Explanations

    goldship

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

    quality, analysis, control

    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
     Tecnología
    0.55
     Usuarios
    0.54
     Technologie
    0.52
    Ě
    0.51
    чни
    0.50
    тров
    0.50
     ஹோ
    0.50
    т
    0.50
    Usuarios
    0.49
     Сергея
    0.49
    POSITIVE LOGITS
     canvas
    0.52
     tiro
    0.50
     ship
    0.50
     seventies
    0.50
     lacquer
    0.49
     IAC
    0.49
     botan
    0.49
     shot
    0.48
     miro
    0.48
     love
    0.48
    Activations Density 0.002%

    No Known Activations