© 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. 91735
    Prev
    Next
    INDEX
    Explanations

    Employee Rights, Clinical predictors

    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
     magasiner
    -0.91
     Arhivirano
    -0.91
    脛
    -0.91
     anteriore
    -0.90
    gigi
    -0.89
    ࿆
    -0.89
     Ini
    -0.89
    
    -0.88
    ﺁ
    -0.88
     bluza
    -0.87
    POSITIVE LOGITS
    return
    0.96
    Estima
    0.96
     beobach
    0.88
    quirer
    0.88
    Портали
    0.88
    appelle
    0.85
    especially
    0.84
    living
    0.84
     a
    0.84
     часто
    0.84
    Activations Density 0.008%

    No Known Activations