© 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. 180245
    Prev
    Next
    INDEX
    Explanations

    multidimensional structure

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

    disclaimers and instructions

    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
    輥
    0.53
     atmosfera
    0.53
     Tarant
    0.49
     Hona
    0.48
     ভোটের
    0.47
     ಮತ
    0.46
     Caz
    0.46
     ಅಭಿಮಾನ
    0.46
    ība
    0.46
    ૄ
    0.46
    POSITIVE LOGITS
    iver
    0.50
    r
    0.49
    Xml
    0.49
    ame
    0.48
    Tables
    0.48
    OU
    0.47
    q
    0.47
    dQ
    0.47
    ampl
    0.46
    ene
    0.46
    Activations Density 0.001%

    No Known Activations