© 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. 139680
    Prev
    Next
    INDEX
    Explanations

    old and new comparisons

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

    laws, prices, platforms, corners

    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
    زين
    0.49
    patient
    0.45
    zam
    0.45
    partition
    0.45
    partial
    0.44
    zett
    0.43
    ﺰ
    0.43
    zigzag
    0.43
    integer
    0.42
    diendo
    0.42
    POSITIVE LOGITS
    е
    0.53
     catchy
    0.50
     പഴയ
    0.49
     leans
    0.48
     Snack
    0.47
    گاهی
    0.47
     bunyi
    0.46
     encapsulates
    0.46
     automatis
    0.46
     Pract
    0.46
    Activations Density 0.001%

    No Known Activations