© 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. 108220
    Prev
    Next
    INDEX
    Explanations

    frequently targeted

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

    ranging from

    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
    e
    0.43
    揚
    0.43
     mayor
    0.43
     compara
    0.42
     tutor
    0.40
     be
    0.40
     “
    0.40
     glyph
    0.40
    做法
    0.40
     b
    0.40
    POSITIVE LOGITS
    ✙
    0.55
    Inserting
    0.54
    ziła
    0.54
     করিলেন
    0.52
     सदैव
    0.52
    सभी
    0.52
    してます
    0.51
    effectuer
    0.50
    AllFilesIn
    0.49
    黼
    0.49
    Activations Density 0.001%

    No Known Activations