© 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. 26177
    Prev
    Next
    INDEX
    Explanations

    common word endings and follow-on words

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

    Updates and configurations

    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
    zan
    0.49
    viel
    0.47
    an
    0.46
    ani
    0.45
    vak
    0.45
     CO
    0.45
     w
    0.44
    vil
    0.44
    kova
    0.44
     L
    0.44
    POSITIVE LOGITS
    ７
    0.55
     strangely
    0.52
    Migrations
    0.50
     структуры
    0.49
    Unexpected
    0.49
    WhiteBalance
    0.49
     élytres
    0.49
    Variables
    0.48
    PERATURE
    0.48
     Até
    0.47
    Activations Density 0.000%

    No Known Activations