© 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. 244314
    Prev
    Next
    INDEX
    Explanations

    specific issues or quantifications

    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
    št
    0.52
    П
    0.48
    ер
    0.47
    М
    0.46
     КА
    0.45
    वित्त
    0.45
    Т
    0.45
    כ
    0.44
    мл
    0.44
    ет
    0.43
    POSITIVE LOGITS
     Coriolis
    0.52
     Engaging
    0.51
     Framing
    0.48
     Resistant
    0.48
     desarrolla
    0.48
    తున్నారు
    0.48
    जापुर
    0.48
     Exposure
    0.48
     পাচ্ছে
    0.47
    argeon
    0.46
    Activations Density 0.001%

    No Known Activations