© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 142182
    Prev
    Next
    INDEX
    Explanations

    subject followed by descriptor

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

    water-resistant

    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
    ారో
    0.54
    ุย
    0.46
    า
    0.45
    ంట్
    0.45
    训
    0.45
     gostar
    0.44
    ısında
    0.44
     તો
    0.44
    要有
    0.43
     yerde
    0.43
    POSITIVE LOGITS
    Cour
    0.51
    ([
    0.49
    Kh
    0.49
    Become
    0.48
    Bulk
    0.47
    Increasing
    0.47
    Adding
    0.47
    Ни
    0.47
    Increased
    0.47
    Lead
    0.46
    Activations Density 0.000%

    No Known Activations