© 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. 84300
    Prev
    Next
    INDEX
    Explanations

    hat trick and scores

    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
    ilitas
    -0.75
    junct
    -0.75
    iální
    -0.74
     establecidos
    -0.74
    گروه
    -0.73
    lymp
    -0.72
    ;//
    -0.71
    DASH
    -0.71
    عد
    -0.69
    )=-\
    -0.69
    POSITIVE LOGITS
     hat
    2.91
     Hat
    2.05
    Hat
    2.02
     hatt
    1.96
    hat
    1.95
     brace
    1.88
    帽子
    1.78
    HAT
    1.77
     hats
    1.74
     HAT
    1.54
    Activations Density 0.009%

    No Known Activations