© 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. 226665
    Prev
    Next
    INDEX
    Explanations

    many or various

    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
    ச்சூழ
    0.66
     भीतर
    0.64
     অতঃপর
    0.63
    ⚖
    0.62
    땐
    0.61
     लिहाजा
    0.60
     எனும்
    0.59
     يُ
    0.59
    🩺
    0.59
    营收
    0.59
    POSITIVE LOGITS
     avere
    0.78
    どんど
    0.77
     nagyon
    0.75
    非常的
    0.71
    但是
    0.68
    或者是
    0.67
    很多的
    0.66
    odore
    0.66
     erine
    0.65
     unele
    0.65
    Activations Density 0.623%

    No Known Activations