© 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. 163498
    Prev
    Next
    INDEX
    Explanations

    mug layout and design

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

    planning routes

    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
    പരമായ
    0.49
     Öğ
    0.48
     Aralık
    0.47
     확장
    0.47
     음악
    0.47
     않
    0.46
     తగ్గ
    0.46
     처리
    0.46
     Ogni
    0.45
     اہمیت
    0.45
    POSITIVE LOGITS
            
    0.50
    ]
    0.48
    né
    0.48
    रा
    0.46
    eware
    0.46
             
    0.46
         
    0.45
                                  
    0.45
    idia
    0.44
     fluoride
    0.44
    Activations Density 0.000%

    No Known Activations