© 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. 167712
    Prev
    Next
    INDEX
    Explanations

    certain prepositions follow words

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

    psychological aspects and states

    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
    ྵ
    0.56
    邗
    0.51
    芗
    0.50
    传感
    0.50
    лый
    0.47
    ileged
    0.47
    াল্ড
    0.47
    РУ
    0.47
    الحضور
    0.46
    Datei
    0.46
    POSITIVE LOGITS
     par
    0.51
     日
    0.51
     Camb
    0.50
     Ο
    0.50
     respect
    0.50
     contro
    0.49
     elementary
    0.49
     Barriers
    0.49
    inton
    0.49
    non
    0.48
    Activations Density 0.000%

    No Known Activations