© 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. 5533
    Prev
    Next
    INDEX
    Explanations

    descriptive attributes and traditions

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

    add dialogue and details

    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
    фа
    0.53
     вечером
    0.50
    食べた
    0.49
    alarının
    0.49
    𝒗
    0.49
    ल्यानंतर
    0.46
    кономи
    0.45
    ราคา
    0.45
    颖
    0.45
    飩
    0.45
    POSITIVE LOGITS
     tradizione
    0.52
     marines
    0.49
     traditions
    0.47
     tradición
    0.47
     tradition
    0.44
     marin
    0.43
     Traditionally
    0.43
     flanks
    0.43
     iconic
    0.43
     بڑی
    0.43
    Activations Density 0.002%

    No Known Activations