© 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. 111400
    Prev
    Next
    INDEX
    Explanations

    opportunities and specific locations

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

    listing examples

    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
     നമഃ
    0.51
    煩
    0.50
    ោគ
    0.50
    ا۔
    0.49
    मूर्ति
    0.49
    vā
    0.47
    Minist
    0.47
     পূর্ববাংলার
    0.46
    文物
    0.46
     različ
    0.46
    POSITIVE LOGITS
    )
    0.54
     "
    0.49
    "
    0.46
     Kne
    0.45
                        
    0.44
     Grafton
    0.43
    0.43
     Cherokee
    0.43
     Redwood
    0.42
          
    0.42
    Activations Density 0.000%

    No Known Activations