© 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. 10-GEMMASCOPE-RES-131K
    4. 119871
    Prev
    Next
    INDEX
    Explanations

    when it comes to

    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
     in
    -2.27
     by
    -1.98
     through
    -1.61
     were
    -1.56
     after
    -1.44
     was
    -1.39
    </b>
    -1.36
    i
    -1.32
     above
    -1.32
     before
    -1.32
    POSITIVE LOGITS
    ⸥
    1.60
     nouvelles
    1.59
    ⎔
    1.56
    
    1.52
    Não
    1.52
    ⃚
    1.52
     nieuwe
    1.49
    ный
    1.49
     Hivatalos
    1.48
     gezegd
    1.48
    Activations Density 0.163%

    No Known Activations