© 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. 97924
    Prev
    Next
    INDEX
    Explanations

    example or hypothetical scenario

    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
    particularly
    -1.42
    especially
    -1.36
    yourself
    -1.31
    calculated
    -1.28
     notamment
    -1.25
    truly
    -1.23
     soprattutto
    -1.20
    尤其是
    -1.20
     comunque
    -1.20
     surtout
    -1.14
    POSITIVE LOGITS
     would
    1.78
     might
    1.62
     then
    1.49
     wouldn
    1.34
     whereas
    1.34
     obviously
    1.32
     Similarly
    1.32
    Obviously
    1.26
     because
    1.25
     tentu
    1.23
    Activations Density 0.080%

    No Known Activations