© 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. 4405
    Prev
    Next
    INDEX
    Explanations

    movie titles and code comments

    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
     tracing
    -0.79
     cum
    -0.76
    Rhode
    -0.75
     contributes
    -0.73
     اليه
    -0.72
    yakit
    -0.71
    mello
    -0.71
     miniature
    -0.71
    برى
    -0.70
    不清
    -0.70
    POSITIVE LOGITS
     Pandora
    1.47
     Avatar
    1.45
    Avatar
    1.40
     Na
    1.23
     RDA
    1.17
    avatar
    1.11
    Na
    1.07
    Pandora
    1.05
     pandora
    1.04
    Recom
    1.02
    Activations Density 0.010%

    No Known Activations