© 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. 170695
    Prev
    Next
    INDEX
    Explanations

    European or international contexts

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

    definitionscategoriesyourmusclescomingeveryonetimeaffectitselfour

    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
    colspan
    0.43
    ૈય
    0.43
    eway
    0.42
     मुह
    0.41
     obstructing
    0.41
    㭂
    0.41
    이야
    0.40
     Contrast
    0.40
    秦
    0.40
    யா
    0.40
    POSITIVE LOGITS
     gastronomic
    0.48
    在全球
    0.48
     supremo
    0.47
    Rank
    0.47
     zaz
    0.45
     zugleich
    0.45
    اتھن
    0.44
     direktor
    0.44
     paket
    0.44
     в
    0.43
    Activations Density 0.001%

    No Known Activations