© 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. 40-GEMMASCOPE-2-RES-16K
    7. 8228
    Prev
    Next
    INDEX
    Explanations

    version numbers and codes

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

    Windows system configuration

    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_40_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    orado
    0.41
    sete
    0.40
    kate
    0.39
    raut
    0.38
     ILLINOIS
    0.37
    PYTHON
    0.36
    digo
    0.36
    caught
    0.36
    osaurus
    0.36
    억
    0.36
    POSITIVE LOGITS
     Token
    0.45
    FileName
    0.44
     chariot
    0.43
     FileName
    0.42
     Kish
    0.42
     Revision
    0.41
    ospin
    0.41
     Фі
    0.41
     build
    0.40
    私募基金
    0.40
    Activations Density 0.020%

    No Known Activations