© 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. 12390
    Prev
    Next
    INDEX
    Explanations

    excitability, excitatory, shallower

    np_acts-logits-general · gemini-2.5-flash-lite

    words related to excitability or activation, particularly in scientific or Asian language contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    胧
    -2.80
    鷙
    -2.75
    
    -2.66
    y
    -2.59
    cknowledge
    -2.44
    ي
    -2.41
     élevés
    -2.30
    颪
    -2.27
     détaillés
    -2.25
    樒
    -2.25
    POSITIVE LOGITS
    $
    3.19
    6
    2.70
    2
    2.63
    3
    2.53
    7
    2.42
    section
    2.34
    1
    2.33
    \
    2.28
     téměř
    2.27
    给
    2.22
    Activations Density 0.002%

    No Known Activations