© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49203
    Prev
    Next
    INDEX
    Explanations

    web requests and urls

    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
     obtainable
    -0.75
    +%
    -0.71
    empt
    -0.70
    ỵ
    -0.70
     ОС
    -0.70
    รี
    -0.70
    ornment
    -0.70
    텔
    -0.69
    য়ে
    -0.68
     במק
    -0.68
    POSITIVE LOGITS
    ロイヤル
    0.65
     Τ
    0.63
    enein
    0.62
    ้อง
    0.61
    hundred
    0.60
     Ciencia
    0.60
    omon
    0.59
     Verbre
    0.59
    gleich
    0.59
     thrown
    0.58
    Activations Density 0.062%

    No Known Activations