© 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. 10-GEMMASCOPE-RES-131K
    7. 11650
    Prev
    Next
    INDEX
    Explanations

    Windows platform

    np_acts-logits-general · gemini-2.5-flash-lite

    the abbreviation "WP" (typically referring to Windows Phone or WordPress in technical contexts).

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    s
    -4.09
    寕
    -2.86
     lae
    -2.81
    ⽼
    -2.75
     bogotá
    -2.64
     rente
    -2.59
    衚
    -2.59
    ’.
    -2.58
    .’
    -2.56
     殼
    -2.50
    POSITIVE LOGITS
     When
    3.06
     During
    2.94
    to
    2.78
     tenacious
    2.72
     If
    2.70
     After
    2.66
     While
    2.66
     disastrous
    2.63
     Within
    2.59
     From
    2.56
    Activations Density 0.001%

    No Known Activations