© 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. 45357
    Prev
    Next
    INDEX
    Explanations

    publication metadata like authors and years

    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
     atter
    -0.76
    かは
    -0.75
    lename
    -0.73
     Sond
    -0.73
    nami
    -0.72
    emie
    -0.71
     indigo
    -0.70
     vard
    -0.70
     Hotline
    -0.70
     alli
    -0.68
    POSITIVE LOGITS
     keywords
    1.64
     tags
    1.43
    tags
    1.36
     genre
    1.35
     authors
    1.35
    keywords
    1.31
     publication
    1.27
     year
    1.26
     Keywords
    1.23
    Keywords
    1.22
    Activations Density 0.097%

    No Known Activations