© 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. 82999
    Prev
    Next
    INDEX
    Explanations

    golden and silver objects

    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
     Georgia
    -0.72
    Сыртқы
    -0.71
     komma
    -0.71
     demi
    -0.71
    bundled
    -0.71
    ertia
    -0.70
     Gleason
    -0.69
    BarButtonItem
    -0.68
    ности
    -0.68
    publicain
    -0.67
    POSITIVE LOGITS
    UKAN
    0.84
     foil
    0.81
     yapıl
    0.79
    GOLD
    0.77
     medal
    0.77
    芪
    0.77
     Foil
    0.77
     aureus
    0.76
     brilliance
    0.76
     placer
    0.75
    Activations Density 0.014%

    No Known Activations