© 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. 164786
    Prev
    Next
    INDEX
    Explanations

    news or specific entities like Inter

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

    increases

    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
    운데
    0.53
    쉼
    0.52
    प्ले
    0.50
    亙
    0.50
    뿐
    0.49
    instrList
    0.48
    <0xBF>
    0.48
    亘
    0.48
    ಿಗೆ
    0.48
    benzoimidazol
    0.47
    POSITIVE LOGITS
     Inter
    0.57
     \
    0.56
        
    0.55
     in
    0.55
     at
    0.54
     ferns
    0.51
          
    0.50
     Corporate
    0.49
     Mrs
    0.49
     Satellite
    0.48
    Activations Density 0.000%

    No Known Activations