© 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. 210209
    Prev
    Next
    INDEX
    Explanations

    evaluation, want, jewel, representatives, prosthesis, will, bar

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

    Unila

    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
    Not in Any Lists

    No Comments

    Negative Logits
    اعه
    0.52
    าย
    0.49
    成長
    0.48
    еру
    0.48
    側
    0.47
    ेश्वर
    0.46
    ჭირ
    0.46
    いが
    0.46
    児童
    0.46
    ή
    0.46
    POSITIVE LOGITS
     elektro
    0.52
    -;
    0.51
     dili
    0.46
     orada
    0.45
     carbonic
    0.45
     للإ
    0.45
     obeyed
    0.45
    argeon
    0.45
     lym
    0.44
     ತ
    0.44
    Activations Density 0.000%

    No Known Activations