© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 33656
    Prev
    Next
    INDEX
    Explanations

    location at the back

    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
     верх
    -0.82
    の外
    -0.80
    btnNew
    -0.79
    DialogTitle
    -0.79
    quedos
    -0.78
    ָא
    -0.74
    SqlDataReader
    -0.74
    Prox
    -0.73
     dúvida
    -0.72
    内外
    -0.72
    POSITIVE LOGITS
     rear
    3.83
    rear
    2.77
    Rear
    2.72
     сзади
    2.61
     behind
    2.50
     Rear
    2.48
     posterior
    2.44
     backend
    2.41
     зад
    2.34
    backend
    2.23
    Activations Density 0.061%

    No Known Activations