© 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. 228421
    Prev
    Next
    INDEX
    Explanations

    economical and, secured software

    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
    ן
    0.49
     असाल
    0.49
    ಾರ್ಟ
    0.44
    Feeling
    0.44
    惀
    0.44
    feeling
    0.43
     ಆದ್ದರಿಂದ
    0.43
    鷳
    0.43
    ಳ
    0.43
     negativity
    0.43
    POSITIVE LOGITS
     primera
    0.50
     مس
    0.48
     khóa
    0.48
     ost
    0.48
     هی
    0.47
     to
    0.47
     première
    0.47
     oste
    0.46
     hâ
    0.46
     लागत
    0.46
    Activations Density 0.000%

    No Known Activations