© 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. 83594
    Prev
    Next
    INDEX
    Explanations

    scattered locations and entities

    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
     two
    -0.97
     it
    -0.89
     for
    -0.86
    万物
    -0.85
     when
    -0.84
     just
    -0.82
     by
    -0.82
     was
    -0.82
     an
    -0.82
     before
    -0.81
    POSITIVE LOGITS
     scattered
    5.13
     spread
    4.03
    scatter
    4.00
    Scatter
    3.66
     dispersed
    3.66
     Scatter
    3.52
     scatter
    3.36
    Spread
    3.30
    spread
    3.28
     Spread
    2.97
    Activations Density 0.166%

    No Known Activations