© 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. 204627
    Prev
    Next
    INDEX
    Explanations

    instructions and financial terms

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

    buying shares or subdirectories

    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
     মেধ
    0.49
     rewriting
    0.47
     Descripción
    0.45
     Jasper
    0.45
     $[\
    0.44
     Andres
    0.43
     phonons
    0.43
     cmake
    0.43
     genc
    0.43
     funcionamiento
    0.42
    POSITIVE LOGITS
    トップス
    0.46
     زيت
    0.46
    ্যান্ট
    0.43
    bagi
    0.43
     శరీర
    0.43
    贅
    0.43
    лам
    0.42
     гало
    0.42
    chandise
    0.41
    उचर
    0.41
    Activations Density 0.001%

    No Known Activations