© 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. 226431
    Prev
    Next
    INDEX
    Explanations

    credits, category, setting, thesis

    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
    Not in Any Lists

    No Comments

    Negative Logits
     fü
    0.52
    sion
    0.52
     développement
    0.50
     théâtre
    0.49
     der
    0.47
    r
    0.47
    gge
    0.46
     políticos
    0.46
    nymi
    0.44
    india
    0.43
    POSITIVE LOGITS
     globalMap
    0.54
     messageShow
    0.49
     Христо
    0.45
     Dispose
    0.44
     சிதம்ப
    0.44
     Gerardo
    0.44
    ዎ
    0.44
     currentColor
    0.43
    ˆ
    0.43
     سود
    0.43
    Activations Density 0.000%

    No Known Activations