© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 100072
    Prev
    Next
    INDEX
    Explanations

    screen and display

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

    the word "display" in technical contexts describing electronic devices and screens.

    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
    7
    -1.81
    .”
    -1.70
    リーの
    -1.57
    6
    -1.55
     Moreover
    -1.53
    diyah
    -1.48
    appré
    -1.47
    !”
    -1.46
     shadowy
    -1.43
    delmi
    -1.39
    POSITIVE LOGITS
     SPECIFICATIONS
    1.48
    皤
    1.48
     Liban
    1.47
     we
    1.45
     темы
    1.43
    ating
    1.41
     следующие
    1.38
     is
    1.38
    𓆸
    1.38
     solicitó
    1.37
    Activations Density 0.064%

    No Known Activations