© 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. 11971
    Prev
    Next
    INDEX
    Explanations

    opening phrases and code snippets

    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
     ferrari
    -0.80
    Étymologie
    -0.78
     leop
    -0.77
    Parc
    -0.74
     Breathable
    -0.71
     ventre
    -0.70
     laurent
    -0.69
     magicians
    -0.69
    ेड
    -0.69
    Drainage
    -0.68
    POSITIVE LOGITS
     Titus
    1.14
    Titus
    0.96
    temuan
    0.84
     Platten
    0.83
     salted
    0.82
    Noten
    0.79
    titus
    0.78
    filas
    0.77
     Tile
    0.75
    slate
    0.75
    Activations Density 0.014%

    No Known Activations