© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 47795
    Prev
    Next
    INDEX
    Explanations

    database keys

    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
     też
    -0.84
     тоже
    -0.79
     电视
    -0.77
     圖片
    -0.76
     GUIDELINES
    -0.76
     戰
    -0.74
     COLUMBIA
    -0.74
     Andromeda
    -0.74
     大き
    -0.73
     贴
    -0.73
    POSITIVE LOGITS
     at
    1.18
    _
    1.11
    ()->
    1.10
     домов
    0.81
     bestow
    0.78
    хами
    0.77
    ilità
    0.77
     would
    0.76
     NOTE
    0.75
     nek
    0.75
    Activations Density 0.009%

    No Known Activations