© 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. 116068
    Prev
    Next
    INDEX
    Explanations

    list item indicators or tags

    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
    eef
    -0.75
    utum
    -0.72
    INF
    -0.71
    NoOf
    -0.71
     cohesive
    -0.69
    otin
    -0.69
     AWESOME
    -0.68
     соответствует
    -0.68
    Nope
    -0.68
    People
    -0.68
    POSITIVE LOGITS
    androidx
    0.87
    movable
    0.79
    发表
    0.77
    ocr
    0.77
    giver
    0.75
     Becher
    0.74
    ють
    0.73
    illig
    0.73
    万元
    0.73
    霄
    0.71
    Activations Density 0.028%

    No Known Activations