© 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. 225317
    Prev
    Next
    INDEX
    Explanations

    describes actions and conditions

    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
    镂
    0.49
     konkur
    0.46
     rom
    0.45
    must
    0.45
    OutputDir
    0.45
    ต้อง
    0.45
     myst
    0.44
     direkt
    0.44
    PlainText
    0.43
    muster
    0.42
    POSITIVE LOGITS
    ﺻ
    0.50
    ρε
    0.48
     chauffeur
    0.47
     ब्रा
    0.44
     feeding
    0.44
    ﺑ
    0.44
    Ặ
    0.44
    ὡ
    0.44
     spades
    0.43
    供
    0.43
    Activations Density 0.000%

    No Known Activations