© 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. 220447
    Prev
    Next
    INDEX
    Explanations

    foreign characters and specific contexts

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

    completely different topics

    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
    穏
    0.52
    м
    0.49
    惕
    0.49
     unfolding
    0.47
    マト
    0.45
    講
    0.45
     enfant
    0.45
     Agn
    0.45
    馴
    0.45
     unruly
    0.44
    POSITIVE LOGITS
    .},
    0.47
    abetic
    0.45
    uko
    0.44
     কানা
    0.43
    arial
    0.42
    oggio
    0.42
    uro
    0.41
     কবর
    0.41
    kappa
    0.41
     গমন
    0.41
    Activations Density 0.000%

    No Known Activations