© 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. 56080
    Prev
    Next
    INDEX
    Explanations

    own distinct characteristics

    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
    Ska
    -0.99
     molte
    -0.97
    ocia
    -0.96
    玢
    -0.93
    nasel
    -0.92
     wichtigsten
    -0.92
    igkeit
    -0.92
     autre
    -0.92
     vários
    -0.91
     numerosi
    -0.91
    POSITIVE LOGITS
     unique
    2.33
     distinct
    1.89
     version
    1.80
     specific
    1.71
     set
    1.69
     way
    1.58
     separate
    1.53
     kind
    1.43
     style
    1.43
     special
    1.36
    Activations Density 0.027%

    No Known Activations