© 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. 153205
    Prev
    Next
    INDEX
    Explanations

    onsite inspections

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

    scientific terms or phrases

    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
     récemment
    0.55
     récent
    0.52
    también
    0.51
    ̀ng
    0.50
    ség
    0.49
    recently
    0.47
    лох
    0.47
    افة
    0.47
    żyć
    0.47
    ᵔ
    0.47
    POSITIVE LOGITS
     foci
    0.44
     современных
    0.44
     Helium
    0.43
     wort
    0.43
     formaldehyde
    0.41
     внутренних
    0.41
     紅
    0.41
     wymag
    0.40
     التيار
    0.40
     ماشینونه
    0.40
    Activations Density 0.000%

    No Known Activations