© 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. 244257
    Prev
    Next
    INDEX
    Explanations

    podcasters, have, you, paste, means, prefer

    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
     brown
    0.46
     its
    0.46
    ácie
    0.44
     benzene
    0.43
     mely
    0.43
     tim
    0.42
     環
    0.42
    indent
    0.42
    loff
    0.42
     returned
    0.42
    POSITIVE LOGITS
    需要在
    0.46
    的要求
    0.46
    kez
    0.46
    으나
    0.46
     oameni
    0.45
    祷
    0.44
    💏
    0.43
    ujesz
    0.43
     gelişt
    0.43
     дополнительные
    0.42
    Activations Density 0.000%

    No Known Activations