© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 115948
    Prev
    Next
    INDEX
    Explanations

    activatable, activists, activation, activators

    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
    ۱۱
    -0.81
    Herzliche
    -0.79
     awfully
    -0.76
    Leistungs
    -0.74
    Wolf
    -0.73
     bemerkt
    -0.73
    Clark
    -0.71
    MenuView
    -0.71
     gewin
    -0.71
     amizade
    -0.71
    POSITIVE LOGITS
    vely
    1.00
    ivel
    0.81
    ive
    0.80
     Anon
    0.77
     DisplayPort
    0.73
    ϭ
    0.73
    ities
    0.72
    想像
    0.70
     DAV
    0.70
     Nec
    0.70
    Activations Density 0.064%

    No Known Activations