© 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. 250578
    Prev
    Next
    INDEX
    Explanations

    distribution options, choose from, end of

    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
     commute
    0.46
    Miles
    0.44
    公里
    0.44
     denunci
    0.43
    Rit
    0.43
     maiden
    0.43
    ధం
    0.42
     +.
    0.42
     -.
    0.42
     pomo
    0.41
    POSITIVE LOGITS
     withstood
    0.51
    𝕨
    0.50
     medicamentos
    0.48
    ಾ
    0.46
    
    0.46
     ছেলেরা
    0.46
    医療
    0.45
    랗
    0.45
     ಕಂಡ
    0.45
    ルス
    0.45
    Activations Density 0.000%

    No Known Activations