© 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. 10-GEMMASCOPE-RES-131K
    7. 9944
    Prev
    Next
    INDEX
    Explanations

    recalling and recall election

    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_10/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
     \
    -2.31
    </u>
    -2.05
     ,
    -2.03
     :
    -2.00
     -
    -1.97
     и
    -1.84
     |
    -1.77
     are
    -1.75
     When
    -1.74
    </h3>
    -1.70
    POSITIVE LOGITS
    鰾
    2.11
    簟
    1.91
     parachoque
    1.91
    麃
    1.86
     publie
    1.84
    簓
    1.82
     própri
    1.81
     camiset
    1.80
     vetores
    1.80
     themſelves
    1.77
    Activations Density 0.006%

    No Known Activations