© 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. 1365
    Prev
    Next
    INDEX
    Explanations

    email 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
     Uniwers
    -0.94
     sun
    -0.86
     Volkes
    -0.84
    Literat
    -0.83
     querida
    -0.81
     wła
    -0.77
     west
    -0.77
     many
    -0.76
     reina
    -0.76
     nebo
    -0.75
    POSITIVE LOGITS
    ptăm
    1.05
    rable
    0.88
     )(
    0.87
     '.')
    0.85
    ási
    0.83
    Must
    0.83
     teljesen
    0.83
    が起こ
    0.83
    úst
    0.82
    。　　
    0.81
    Activations Density 0.004%

    No Known Activations