© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 91857
    Prev
    Next
    INDEX
    Explanations

    historical events

    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
    了一眼
    -0.94
    izate
    -0.93
    ceuticals
    -0.90
    cheme
    -0.88
    istic
    -0.88
    robots
    -0.87
     vuitton
    -0.84
    尺寸
    -0.84
    morphosis
    -0.84
     treachery
    -0.84
    POSITIVE LOGITS
     history
    3.22
     historical
    2.47
    history
    2.31
    History
    2.22
     History
    2.20
     истории
    2.05
     examples
    1.99
     histories
    1.98
    historical
    1.92
     HISTORY
    1.91
    Activations Density 0.063%

    No Known Activations