© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 118307
    Prev
    Next
    INDEX
    Explanations

    copyright notices and headers

    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
     as
    -0.88
     ziehen
    -0.84
     coo
    -0.81
     although
    -0.78
    ဂ
    -0.76
    鵬
    -0.75
     dra
    -0.74
     chociaż
    -0.73
    Oy
    -0.73
    tider
    -0.72
    POSITIVE LOGITS
    ләр
    0.93
    greet
    0.85
    roën
    0.82
     umano
    0.80
    quinas
    0.79
     inconvénients
    0.77
     réalisateur
    0.75
     politi
    0.75
     Lancer
    0.74
    such
    0.74
    Activations Density 0.059%

    No Known Activations