© 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. 73432
    Prev
    Next
    INDEX
    Explanations

    64-bit systems

    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
     sixty
    -0.83
    6
    -0.80
     Embar
    -0.77
    Roc
    -0.75
    cias
    -0.75
    Leon
    -0.74
    SELECTED
    -0.73
    ctar
    -0.72
    を増
    -0.71
     strode
    -0.71
    POSITIVE LOGITS
     Gleaner
    0.75
     SYMBOL
    0.73
     प्रयोग
    0.71
     kerajaan
    0.67
     compil
    0.66
    uminense
    0.65
     romain
    0.65
    Gps
    0.65
    หมาย
    0.65
    ulsive
    0.65
    Activations Density 0.031%

    No Known Activations