© 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. 24816
    Prev
    Next
    INDEX
    Explanations

    I am, I intended, I must

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

    be, Besch prefixes

    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
    şil
    0.47
    ᓕ
    0.47
     eficaz
    0.46
    ორცი
    0.46
    <unused48>
    0.46
     ہوگا۔
    0.45
     ефектив
    0.44
    Stylish
    0.43
    に参加
    0.43
    <unused86>
    0.43
    POSITIVE LOGITS
     všech
    0.47
    dou
    0.44
    all
    0.41
    two
    0.41
     всех
    0.41
    drive
    0.41
    d
    0.40
    dye
    0.39
    three
    0.38
     inhabit
    0.38
    Activations Density 0.016%

    No Known Activations