© 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. 10-GEMMASCOPE-RES-131K
    7. 74607
    Prev
    Next
    INDEX
    Explanations

    e.g.:

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

    The neuron fires on the e.g. example‐introducing abbreviation (i.e. the “e.g. :” sequence of tokens).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    $
    -3.03
    "
    -2.92
    嗵
    -2.86
    愎
    -2.81
    clientY
    -2.81
     atau
    -2.80
    \
    -2.78
    right
    -2.61
    涐
    -2.58
    what
    -2.55
    POSITIVE LOGITS
     “
    3.73
    ’
    3.00
     lessening
    2.95
     “…
    2.88
     lessen
    2.83
     “[
    2.70
     Dingen
    2.66
    瘸
    2.55
    archiwizowane
    2.50
     overarching
    2.47
    Activations Density 0.001%

    No Known Activations