© 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. 10-GEMMASCOPE-RES-131K
    7. 104162
    Prev
    Next
    INDEX
    Explanations

    IAP or Fool

    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_10/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
    _
    -2.19
    玏
    -2.05
     There
    -2.03
     While
    -1.98
     Many
    -1.96
    
    -1.93
     It
    -1.92
    In
    -1.88
    There
    -1.88
     Capítulo
    -1.85
    POSITIVE LOGITS
    ⸫
    2.13
    型的
    2.11
    垕
    2.08
     incredibly
    2.06
    in
    2.02
    '
    1.98
     imagined
    1.91
    
    1.90
    end
    1.88
    jaqueta
    1.87
    Activations Density 0.006%

    No Known Activations