© 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. 198252
    Prev
    Next
    INDEX
    Explanations

    Oliver Wagner

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

    wave displacement

    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
     DROP
    0.52
     干
    0.51
     takers
    0.51
     cellophane
    0.49
    会对
    0.49
     γ
    0.48
     adata
    0.46
     soften
    0.46
     holders
    0.46
     elenco
    0.45
    POSITIVE LOGITS
    बी
    0.52
    mi
    0.51
    to
    0.49
    their
    0.49
    м
    0.49
     जिसका
    0.46
     त्यांचा
    0.45
    ها
    0.45
    land
    0.44
    תו
    0.44
    Activations Density 0.001%

    No Known Activations