© 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. 45228
    Prev
    Next
    INDEX
    Explanations

    technical attributes and links

    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
     sju
    -0.73
     Comando
    -0.71
     治
    -0.71
    MANUEL
    -0.69
     marki
    -0.68
    Кры
    -0.68
     nawr
    -0.67
    dialogs
    -0.67
     tenden
    -0.66
     ستاره
    -0.66
    POSITIVE LOGITS
    Good
    0.72
     Good
    0.70
    isMobile
    0.69
     chiam
    0.67
     good
    0.67
    굿
    0.64
    Limitation
    0.63
     llamada
    0.62
    Asoci
    0.62
     Van
    0.61
    Activations Density 0.050%

    No Known Activations