© 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. 103460
    Prev
    Next
    INDEX
    Explanations

    “breadcrumb”

    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
    tage
    -0.90
     instant
    -0.80
    jah
    -0.79
     developmental
    -0.77
    controls
    -0.77
    RS
    -0.76
     dingin
    -0.76
    printed
    -0.75
    fprintf
    -0.75
    伅
    -0.75
    POSITIVE LOGITS
    ชั่น
    0.77
    훨
    0.77
     anybody
    0.77
     recomendada
    0.77
     watching
    0.76
    getMain
    0.74
     advierte
    0.74
     sooooo
    0.73
     here
    0.73
     recommended
    0.71
    Activations Density 0.003%

    No Known Activations