© 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. 91514
    Prev
    Next
    INDEX
    Explanations

    car believed to have been involved

    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
     पहु
    -0.83
    Cum
    -0.80
     instead
    -0.79
    常常
    -0.79
     even
    -0.78
     $
    -0.78
     finally
    -0.76
     already
    -0.75
     Cum
    -0.73
    データ
    -0.73
    POSITIVE LOGITS
     serpiente
    1.10
     unwell
    1.01
     believed
    1.01
     neumáticos
    0.98
    μβρίου
    0.95
    内置
    0.94
    ڼ
    0.91
     locura
    0.88
     ({
    0.87
    引き続き
    0.87
    Activations Density 0.026%

    No Known Activations