© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 81673
    Prev
    Next
    INDEX
    Explanations

    reading body content

    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
    坷
    -0.86
     wypeł
    -0.78
     innerhalb
    -0.75
    ęgn
    -0.74
    ഓ
    -0.71
     gleicher
    -0.69
     bowler
    -0.69
    gola
    -0.68
     he
    -0.68
     memanggil
    -0.67
    POSITIVE LOGITS
     body
    1.52
     stream
    1.45
     streams
    1.36
     streaming
    1.23
     Stream
    1.23
    body
    1.21
     content
    1.20
     Body
    1.15
     entity
    1.10
    getBody
    1.09
    Activations Density 0.051%

    No Known Activations