© 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. 76941
    Prev
    Next
    INDEX
    Explanations

    penalties and prison sentences

    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
     boucle
    -0.84
    ítulos
    -0.81
    маны
    -0.80
     vols
    -0.79
    
    -0.77
    degenerative
    -0.77
     lỗi
    -0.76
     graphically
    -0.75
    netbeans
    -0.74
     tablespoon
    -0.73
    POSITIVE LOGITS
     possible
    1.09
     up
    1.05
     akár
    1.03
    最大
    1.03
     maximum
    1.03
     pouvant
    1.00
     potrebbero
    0.98
    MAXIMUM
    0.98
     potential
    0.96
     podendo
    0.94
    Activations Density 0.014%

    No Known Activations