© 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. 1354
    Prev
    Next
    INDEX
    Explanations

    HTML element selectors and attributes

    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_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
     should
    -2.05
     on
    -1.96
     After
    -1.88
     for
    -1.84
     have
    -1.82
     must
    -1.66
     prevent
    -1.65
     chose
    -1.65
     put
    -1.62
     went
    -1.61
    POSITIVE LOGITS
    ܇
    1.85
    ሺ
    1.69
     中國
    1.66
     概要
    1.63
    ApiModelProperty
    1.63
    recently
    1.59
    rodalom
    1.58
    relatively
    1.57
     gewi
    1.57
    泚
    1.55
    Activations Density 0.002%

    No Known Activations