© 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. 115026
    Prev
    Next
    INDEX
    Explanations

    numbers and facts

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

    concerning, alone, System, foods, reflection

    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
    ！（
    0.46
    <unused416>
    0.43
    Ĺ
    0.42
    <unused689>
    0.41
     सिंपली
    0.41
    
    0.40
    ![
    0.39
     टेक्नोलॉजी
    0.39
     Джу
    0.39
    <unused190>
    0.39
    POSITIVE LOGITS
     durant
    0.52
     أيضا
    0.49
     also
    0.47
     myocardium
    0.46
     before
    0.46
     additionally
    0.45
     aqueous
    0.44
     Thirdly
    0.44
     there
    0.44
     Ammonia
    0.44
    Activations Density 0.002%

    No Known Activations