© 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. 69912
    Prev
    Next
    INDEX
    Explanations

    change or increase magnitude

    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
     Amts
    -0.92
    良好
    -0.84
     '../../
    -0.84
     aktar
    -0.82
    妓
    -0.81
     exam
    -0.79
    街
    -0.78
    諳
    -0.77
     retrieval
    -0.77
     eruption
    -0.77
    POSITIVE LOGITS
     rate
    0.99
     the
    0.94
     WIP
    0.89
     magnitude
    0.86
     intensity
    0.85
     conforma
    0.85
     size
    0.80
     בישראל
    0.80
     level
    0.80
     athe
    0.79
    Activations Density 0.017%

    No Known Activations