© 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. 244474
    Prev
    Next
    INDEX
    Explanations

    dating, weather, sports, moral

    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
     தொகை
    0.59
    肿瘤
    0.57
     اجتماعی
    0.55
    asos
    0.53
    (_.
    0.53
    운동
    0.52
    ุ
    0.52
     غیر
    0.51
    isode
    0.51
     സംഘടന
    0.51
    POSITIVE LOGITS
     Con
    0.49
     "
    0.49
     rate
    0.48
     script
    0.47
     first
    0.47
     HD
    0.46
     revolution
    0.45
     Agile
    0.45
     IIT
    0.45
     Lin
    0.44
    Activations Density 0.002%

    No Known Activations