© 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. 37934
    Prev
    Next
    INDEX
    Explanations

    header guards and copyright notices

    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
     Ready
    -0.74
     Practical
    -0.69
     チェーン
    -0.67
     Blackberry
    -0.67
    InThe
    -0.67
    ◕
    -0.66
    挙げ
    -0.65
     Myrtle
    -0.65
     MPR
    -0.65
     위
    -0.64
    POSITIVE LOGITS
    Alexand
    0.79
     जल
    0.75
    dists
    0.71
    ずら
    0.68
    TRA
    0.68
    ೆಯ
    0.68
    siswa
    0.66
    ništvo
    0.65
     pouch
    0.65
    里斯
    0.64
    Activations Density 0.047%

    No Known Activations