© 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. 108165
    Prev
    Next
    INDEX
    Explanations

    Pra prefix

    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
    ẩu
    -0.81
     Immunity
    -0.77
     abstracto
    -0.76
     kanilang
    -0.75
    OTION
    -0.71
    ｨ
    -0.71
    amint
    -0.71
     televisión
    -0.71
    節約
    -0.71
    節目
    -0.71
    POSITIVE LOGITS
    Пра
    1.11
     Pra
    1.02
     Пра
    1.00
     pra
    0.96
     روشن
    0.85
    Pra
    0.82
    htbp
    0.82
     Aufenthalts
    0.80
     Présentation
    0.79
     пра
    0.77
    Activations Density 0.028%

    No Known Activations