© 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. 58875
    Prev
    Next
    INDEX
    Explanations

    numbered lists and points

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

    I or $ with math/AI descriptions

    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
    μον
    0.53
    ാര്‍
    0.51
     ।
    0.45
     Độ
    0.43
    omorf
    0.42
     dirinya
    0.42
    дії
    0.41
    ју
    0.41
     ölç
    0.41
    íguez
    0.40
    POSITIVE LOGITS
    Tipo
    0.40
    碌
    0.39
    tags
    0.39
    お手
    0.38
     perch
    0.38
    ต้องการ
    0.38
     Prussians
    0.38
     Banco
    0.38
     Madeira
    0.38
     deserve
    0.38
    Activations Density 0.000%

    No Known Activations