© 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. 40042
    Prev
    Next
    INDEX
    Explanations

    اختيار الاس, ibn, benvenuto

    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
    \
    -2.17
     was
    -2.16
     is
    -2.13
    MAXN
    -1.93
     It
    -1.89
    出了一
    -1.86
    を
    -1.85
     Of
    -1.83
     '-':
    -1.77
    на
    -1.73
    POSITIVE LOGITS
    ↵
    2.72
    钨
    2.06
    kowym
    1.98
    㩒
    1.89
    続きます
    1.87
     véritable
    1.87
    
    1.83
    唻
    1.79
    ſelves
    1.77
     kjer
    1.77
    Activations Density 0.001%

    No Known Activations