© 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. 60492
    Prev
    Next
    INDEX
    Explanations

    code syntax characters

    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
     traits
    -0.87
     fests
    -0.83
    BACK
    -0.83
    鋨
    -0.82
     both
    -0.81
    En
    -0.81
     paragraphs
    -0.79
    amin
    -0.79
    Both
    -0.78
    While
    -0.77
    POSITIVE LOGITS
    Fuji
    0.89
    DOCX
    0.88
    arusian
    0.87
    contri
    0.86
    etap
    0.84
     همین
    0.82
     troisième
    0.82
     така
    0.81
    fabrik
    0.79
    donna
    0.79
    Activations Density 0.020%

    No Known Activations