© 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. 90458
    Prev
    Next
    INDEX
    Explanations

    linux kernel includes

    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
     Umständen
    -0.74
     SURVEY
    -0.70
    ioctl
    -0.67
    тельная
    -0.67
    INSTANCE
    -0.67
    Survey
    -0.67
    casecmp
    -0.66
    طف
    -0.66
    unuz
    -0.65
    選手権
    -0.64
    POSITIVE LOGITS
     shells
    0.74
    视野
    0.71
    模块
    0.69
     gunfire
    0.68
     Rabin
    0.68
     victor
    0.67
    紫色
    0.67
     thio
    0.66
     threads
    0.66
     trad
    0.66
    Activations Density 0.056%

    No Known Activations