© 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. 83338
    Prev
    Next
    INDEX
    Explanations

    reserved access

    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
    effect
    -0.71
    artes
    -0.66
    нус
    -0.66
    rtner
    -0.66
     unsc
    -0.66
    sources
    -0.66
    wska
    -0.65
     Screens
    -0.64
     netting
    -0.64
     overdo
    -0.64
    POSITIVE LOGITS
    junit
    0.71
    Julian
    0.70
    λέ
    0.69
     Mand
    0.68
     Julian
    0.68
    Mand
    0.67
    unix
    0.66
     esetben
    0.66
     painel
    0.65
    อนไลน์
    0.65
    Activations Density 0.063%

    No Known Activations