© 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. 11628
    Prev
    Next
    INDEX
    Explanations

    government titles or sections

    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
     it
    -2.08
     a
    -2.03
     when
    -1.91
     if
    -1.82
     with
    -1.81
     an
    -1.75
     by
    -1.74
     on
    -1.69
     might
    -1.68
    ers
    -1.63
    POSITIVE LOGITS
    itisation
    2.19
     *
    
    2.02
     maniere
    1.96
    좆
    1.81
    {})
    1.81
    ludes
    1.80
     ſame
    1.77
     cabine
    1.76
    `,
    
    1.76
    <>();
    
    1.74
    Activations Density 0.004%

    No Known Activations