© 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. 99638
    Prev
    Next
    INDEX
    Explanations

    replies, comments, and information

    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
     especially
    -0.82
     também
    -0.81
    JKLM
    -0.81
     见
    -0.79
    kset
    -0.79
     إلى
    -0.79
     ","
    -0.79
    ⊖
    -0.77
    
    -0.77
     hoga
    -0.76
    POSITIVE LOGITS
    polling
    0.89
     jednej
    0.86
    の方
    0.86
     ameste
    0.86
     singur
    0.84
     rápidamente
    0.82
    パネル
    0.82
     miejsce
    0.82
     laquelle
    0.80
    之力
    0.79
    Activations Density 0.004%

    No Known Activations