© 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. 22-GEMMASCOPE-RES-131K
    7. 93166
    Prev
    Next
    INDEX
    Explanations

    numbers and arithmetic

    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_22/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
     also
    -1.67
     likewise
    -1.21
     is
    -1.20
     will
    -1.17
    <bos>
    -1.09
    了一遍
    -1.05
     همچنین
    -0.95
    現象
    -0.95
     was
    -0.94
     again
    -0.94
    POSITIVE LOGITS
    danh
    1.18
     véhicules
    1.10
     ontvang
    1.07
     gewähr
    1.05
     sillä
    1.01
     cérami
    1.00
    ibat
    1.00
    tranh
    0.99
    ــــــــ
    0.98
     assise
    0.98
    Activations Density 0.016%

    No Known Activations