© 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. 238979
    Prev
    Next
    INDEX
    Explanations

    numbers and foreign words

    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
    keletal
    0.46
     espíritu
    0.45
     সাগর
    0.45
    ）；
    0.44
     पंकज
    0.44
     ዕ
    0.43
    amante
    0.43
     אר
    0.43
    াদিগকে
    0.43
    msbuild
    0.43
    POSITIVE LOGITS
    ابق
    0.49
     nærm
    0.48
    غير
    0.47
     lực
    0.45
     prvi
    0.45
    優先
    0.45
     نفر
    0.44
     meios
    0.44
    首先
    0.44
    력
    0.44
    Activations Density 0.001%

    No Known Activations