© 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. 22-GEMMASCOPE-RES-131K
    7. 27222
    Prev
    Next
    INDEX
    Explanations

    Quantifying or emphasizing statements

    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_22/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
     οποίο
    -0.82
    Élet
    -0.82
    ত
    -0.82
    énus
    -0.81
    voce
    -0.81
    ukt
    -0.80
     restantes
    -0.79
    믿
    -0.78
    poort
    -0.77
    ۥ
    -0.77
    POSITIVE LOGITS
     even
    1.16
     bahkan
    1.13
     akár
    1.12
     zelfs
    1.11
     jopa
    1.06
     approximately
    1.05
     incluso
    1.05
     تقری
    1.02
     навіть
    1.01
     roughly
    0.99
    Activations Density 0.128%

    No Known Activations