© 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. 90304
    Prev
    Next
    INDEX
    Explanations

    being involved in

    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
     vastly
    -1.10
     devoid
    -1.09
     excelencia
    -1.06
    A
    -1.02
     menyebabkan
    -1.00
    甞
    -1.00
    kové
    -0.98
    orges
    -0.98
    饜
    -0.96
    κια
    -0.96
    POSITIVE LOGITS
     in
    2.92
     with
    1.31
    ในการ
    1.16
    involved
    1.08
     Either
    1.07
     Muitos
    1.07
    atoshi
    1.05
     Entonces
    1.04
     във
    1.04
     penyanyi
    1.02
    Activations Density 0.023%

    No Known Activations