© 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. 52982
    Prev
    Next
    INDEX
    Explanations

    powerful, overall

    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
    NotFoundError
    0.51
    that
    0.50
    ð
    0.50
    í
    0.48
    ia
    0.47
    base
    0.47
    les
    0.46
    ria
    0.46
    iga
    0.46
    特
    0.46
    POSITIVE LOGITS
     cursing
    0.56
     waving
    0.55
     sobbing
    0.52
     dipping
    0.52
     déprimées
    0.52
     distraught
    0.50
    鬢
    0.50
     sinnv
    0.50
     amiss
    0.50
     splashing
    0.49
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.