© 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. 119780
    Prev
    Next
    INDEX
    Explanations

    able to, caught for, serious side, national railways, Mentors

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

    examples, commentary, messages

    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
    𝚐
    0.52
     අය
    0.51
    ilj
    0.49
    તિહાસ
    0.48
    libat
    0.48
     étudiants
    0.48
     baya
    0.48
    ગાહી
    0.47
    ibat
    0.47
    dives
    0.47
    POSITIVE LOGITS
    ?"
    0.61
    4
    0.57
    6
    0.56
    1
    0.54
    5
    0.53
    "
    0.52
     NOT
    0.50
     ..."
    0.50
     "
    0.49
     $\
    0.49
    Activations Density 0.000%

    No Known Activations