© 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. 107337
    Prev
    Next
    INDEX
    Explanations

    Copyright notice

    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
     in
    -1.16
     to
    -0.96
     of
    -0.95
     as
    -0.86
     at
    -0.85
     on
    -0.84
    ->$
    -0.81
     from
    -0.80
     because
    -0.79
     damit
    -0.79
    POSITIVE LOGITS
     prachtige
    1.01
    
    0.96
    utveck
    0.94
     refroid
    0.94
     grijs
    0.92
     fluctuating
    0.91
     réuss
    0.90
     pratiquer
    0.90
     publier
    0.89
     pourra
    0.89
    Activations Density 0.003%

    No Known Activations