© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 44166
    Prev
    Next
    INDEX
    Explanations

    symbolic gesture or interaction

    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_10/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
     '
    -2.86
     What
    -2.84
     The
    -2.22
                 
    -2.16
    ll
    -2.09
                  
    -2.09
           
    -2.08
     menghapus
    -2.03
    不是
    -2.03
     When
    -2.03
    POSITIVE LOGITS
    臯
    2.72
    呖
    2.30
    هما
    2.22
    iffance
    2.22
    Ꮔ
    2.20
     CHEMISTRY
    2.14
    
    2.11
    趼
    2.11
    ,“
    2.09
    ጵ
    2.09
    Activations Density 0.005%

    No Known Activations