© 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. 133772
    Prev
    Next
    INDEX
    Explanations

    happy, optimum, ranging, range, path

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

    Russian, cartoon, models

    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
    πουργ
    0.48
    hluk
    0.45
    ט
    0.45
    sobre
    0.44
    mluv
    0.44
    ogany
    0.43
     marriages
    0.43
    Ces
    0.43
    BlockFit
    0.43
    ड
    0.43
    POSITIVE LOGITS
     Kr
    0.50
     Zack
    0.47
     Ki
    0.46
     spontaneously
    0.46
     Artemis
    0.46
     Fairmont
    0.45
    ِين
    0.44
     Evil
    0.44
     raging
    0.44
    ِينَ
    0.43
    Activations Density 0.001%

    No Known Activations