© 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. 198772
    Prev
    Next
    INDEX
    Explanations

    Black Summer season

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

    non technical

    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
    ški
    0.54
     laranja
    0.50
     تلك
    0.44
     δὲ
    0.43
    '};
    0.43
     সেগুলো
    0.42
     цве
    0.42
     irgendwie
    0.41
    color
    0.41
    পিন
    0.40
    POSITIVE LOGITS
    neither
    0.47
    ꯡ
    0.47
     Neither
    0.47
     neither
    0.46
    जे
    0.43
    िवेशन
    0.42
     commencing
    0.42
    ඤ
    0.41
    роваться
    0.39
     protects
    0.39
    Activations Density 0.000%

    No Known Activations