© 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. 73402
    Prev
    Next
    INDEX
    Explanations

    Reserve our, FREE SHIPPING, bug assigned

    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
     cubos
    -0.79
     Scoop
    -0.73
    的世界
    -0.70
    Wound
    -0.69
    permit
    -0.69
    mín
    -0.69
    hueta
    -0.69
     descuento
    -0.69
    hatenablog
    -0.69
    ":{"
    -0.68
    POSITIVE LOGITS
     bugs
    1.11
     Bugs
    1.10
     whiteboard
    0.98
     Assigned
    0.95
     bug
    0.93
    Assign
    0.92
    Bug
    0.92
    assigned
    0.92
     assigned
    0.91
    Assigned
    0.91
    Activations Density 0.062%

    No Known Activations