© 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. 104645
    Prev
    Next
    INDEX
    Explanations

    you will support either way

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

    jokelplay on 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
    ú
    0.50
    áb
    0.50
    áll
    0.49
    ade
    0.49
     つ
    0.49
     ହ
    0.49
    mun
    0.48
     rú
    0.46
    curses
    0.46
    mt
    0.45
    POSITIVE LOGITS
    شتی
    0.48
     artificielle
    0.46
    രുടെയും
    0.46
    менов
    0.46
     doğrudan
    0.44
    与其
    0.44
    شى
    0.44
     BlueprintName
    0.44
    湾
    0.44
     menyelesaikan
    0.43
    Activations Density 0.000%

    No Known Activations