© 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. 118091
    Prev
    Next
    INDEX
    Explanations

    areas and regions

    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
    ごち
    -0.89
    ApiProperty
    -0.85
     MUNICIP
    -0.83
    𝒾
    -0.79
    ressional
    -0.79
    thered
    -0.79
    ギリス
    -0.79
     uiter
    -0.78
    präch
    -0.77
     membrana
    -0.77
    POSITIVE LOGITS
     areas
    5.66
    Areas
    3.92
    areas
    3.86
     regions
    3.81
     Areas
    3.72
     sections
    3.33
     áreas
    3.30
     spots
    3.27
     portions
    3.27
     parts
    3.22
    Activations Density 0.250%

    No Known Activations