© 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. 153652
    Prev
    Next
    INDEX
    Explanations

    sale or notice

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

    numbers and sales figures

    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
    ↵
    0.48
    یر
    0.47
    ich
    0.47
    gment
    0.47
    َاب
    0.47
    وری
    0.45
     sombre
    0.44
    ầy
    0.44
    줌
    0.44
     whale
    0.43
    POSITIVE LOGITS
    t
    0.57
    curses
    0.56
    Loksatta
    0.47
    𝘧
    0.47
    didn
    0.47
     खाते
    0.46
     договору
    0.45
    ｂ
    0.45
    Bsky
    0.45
    laus
    0.45
    Activations Density 0.000%

    No Known Activations