© 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. 201921
    Prev
    Next
    INDEX
    Explanations

    multilingual text fragments

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

    require documentation

    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
     Weston
    0.52
     instantaneously
    0.50
     instantly
    0.49
     considered
    0.47
    //
    0.46
     exclusively
    0.46
     Meredith
    0.45
    \\
    0.45
     immediately
    0.45
     Weber
    0.44
    POSITIVE LOGITS
     ற
    0.55
    ɱ
    0.52
     सरसों
    0.51
     เห็น
    0.49
    वर्गीय
    0.49
     மற்ற
    0.48
     सौर
    0.48
     ក
    0.47
    dyž
    0.47
    स्परिक
    0.47
    Activations Density 0.000%

    No Known Activations