© 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. 45617
    Prev
    Next
    INDEX
    Explanations

    Full HD display

    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
     informatique
    -0.75
     computer
    -0.73
    hotmail
    -0.72
     telewiz
    -0.71
    OLED
    -0.71
     persecution
    -0.69
    шее
    -0.69
    setTexture
    -0.69
     persoonlijke
    -0.69
     computerized
    -0.68
    POSITIVE LOGITS
     resistive
    1.16
     WV
    1.03
    capac
    0.90
    зировать
    0.89
     Anz
    0.89
    luor
    0.84
     Capac
    0.80
     bright
    0.78
     смотреть
    0.77
    Res
    0.77
    Activations Density 0.043%

    No Known Activations