© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 64637
    Prev
    Next
    INDEX
    Explanations

    speaking of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    りましたが
    -0.99
    
    -0.96
     snak
    -0.94
    罰
    -0.94
    justed
    -0.92
    lorn
    -0.92
    🙍
    -0.91
     deler
    -0.91
    ❫
    -0.91
    葉
    -0.90
    POSITIVE LOGITS
     of
    2.05
     strictly
    1.59
     purely
    1.29
     from
    1.23
     personally
    1.05
     speaking
    1.05
     is
    1.00
     specifically
    0.98
     reminds
    0.96
     realistically
    0.96
    Activations Density 0.008%

    No Known Activations