© 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. 174224
    Prev
    Next
    INDEX
    Explanations

    approved rules

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

    understanding classifications

    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
    㐹
    0.51
    ajat
    0.46
     उदाहरण
    0.46
     বিধি
    0.46
     कार्यकारी
    0.46
     构建
    0.45
     ලබා
    0.44
     प्लांट
    0.44
     वेरिएबल
    0.44
     calcule
    0.44
    POSITIVE LOGITS
    an
    0.64
    ان
    0.61
    나
    0.59
    it
    0.59
    는
    0.54
    다
    0.52
    에
    0.51
    시
    0.50
    그
    0.49
    안
    0.49
    Activations Density 0.001%

    No Known Activations