© 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. 121169
    Prev
    Next
    INDEX
    Explanations

    printable form, All draws, lenders have

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

    predictable mathematical simplification

    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
    ਮ
    0.60
    म
    0.58
    ܕ
    0.58
    स
    0.56
    ाम
    0.55
    ის
    0.54
    ավ
    0.54
    ի
    0.54
    𝗮
    0.53
    дії
    0.52
    POSITIVE LOGITS
     extrapolation
    0.46
     عنها
    0.46
    嵌入
    0.44
     Eqs
    0.44
     softmax
    0.41
     inroads
    0.41
    矩阵
    0.40
     DRN
    0.39
     mappings
    0.39
     decarbon
    0.39
    Activations Density 0.000%

    No Known Activations