© 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. 110804
    Prev
    Next
    INDEX
    Explanations

    FilenameFiled inFiled underFile > SaveFile > Preferences

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

    file paths and options

    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
    を一
    0.48
     ocurrió
    0.46
     dplyr
    0.45
    ✔️
    0.43
     فقط
    0.43
     Anosov
    0.42
     absolument
    0.41
     нео
    0.41
    కపో
    0.41
     indispensables
    0.40
    POSITIVE LOGITS
     ভিডিও
    0.41
    texture
    0.40
    视频
    0.40
    ρας
    0.40
     বোধ
    0.39
     박
    0.39
    descricao
    0.39
    wedd
    0.39
    streets
    0.39
    reflected
    0.39
    Activations Density 0.000%

    No Known Activations