© 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. 57191
    Prev
    Next
    INDEX
    Explanations

    insurable properties or hospitals designed

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

    hours viewed

    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
     Andean
    0.50
    ר
    0.48
    compareTo
    0.45
     Westen
    0.44
    Avec
    0.43
    Những
    0.43
    ර්ධ
    0.43
    А
    0.43
     Những
    0.43
     Dapat
    0.43
    POSITIVE LOGITS
     webbrowser
    0.45
    tte
    0.43
    dai
    0.43
    招呼
    0.42
     fluctuation
    0.42
     arterial
    0.41
    amélioration
    0.41
    jump
    0.41
    ti
    0.40
    ipu
    0.40
    Activations Density 0.000%

    No Known Activations