© 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. 167666
    Prev
    Next
    INDEX
    Explanations

    common words followed by descriptive words

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

    sensory descriptions, examples, or types

    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
    2
    0.43
    February
    0.39
    <start_of_image>
    0.39
     critically
    0.39
     new
    0.38
    1
    0.38
     February
    0.37
     anxiety
    0.37
    7
    0.37
    new
    0.35
    POSITIVE LOGITS
     cosidd
    0.56
     ebenfalls
    0.50
     sogenannte
    0.48
     sogen
    0.48
     tohoto
    0.48
    こうした
    0.47
     కూడా
    0.44
     bijvoorbeeld
    0.44
     apapun
    0.43
    ногда
    0.43
    Activations Density 0.128%

    No Known Activations