© 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. 176736
    Prev
    Next
    INDEX
    Explanations

    enough Daily Challenges

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

    limited quantity or size

    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
    '
    0.55
    yka
    0.51
    an
    0.50
    JO
    0.49
    jo
    0.49
    एस
    0.47
    iko
    0.47
    琀
    0.46
     volna
    0.46
    aning
    0.46
    POSITIVE LOGITS
     ಕಡಿಮೆ
    0.46
    欧
    0.46
    iseaux
    0.44
    ுள்ளார்
    0.44
    राबरी
    0.43
     kitchenette
    0.43
    壊
    0.42
     cropped
    0.42
    scriptsize
    0.42
    temper
    0.42
    Activations Density 0.000%

    No Known Activations