© 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. 17017
    Prev
    Next
    INDEX
    Explanations

    units of measurement

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

    model size and unit measurements

    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
     আগ্রহ
    0.57
    <unused2221>
    0.57
     кількість
    0.52
     संख्या
    0.51
     ধরন
    0.51
    ృద్ధి
    0.50
    వృద్ధి
    0.50
     श्रेणियों
    0.49
     நேரம்
    0.49
     సంవ
    0.49
    POSITIVE LOGITS
    짜
    0.64
    씩
    0.55
     (!)
    0.51
     version
    0.49
     pump
    0.49
    (!)
    0.48
     monstros
    0.48
     mini
    0.47
     stom
    0.47
     program
    0.46
    Activations Density 0.133%

    No Known Activations