© 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. 73632
    Prev
    Next
    INDEX
    Explanations

    time, day, polling, passenger, controls

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

    being specific

    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
     Promotional
    0.46
     resembles
    0.42
     resembling
    0.41
    附加
    0.40
     negotiable
    0.39
     promotional
    0.39
    附
    0.39
     a
    0.38
     neatly
    0.38
    <unused1030>
    0.38
    POSITIVE LOGITS
     zdecyd
    0.45
     większość
    0.45
     berk
    0.42
     vraag
    0.42
    isz
    0.42
     tiszt
    0.41
     rempl
    0.41
    day
    0.40
     lutte
    0.40
     tutte
    0.40
    Activations Density 0.000%

    No Known Activations