© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 73714
    Prev
    Next
    INDEX
    Explanations

    to explain or list examples

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

    The neuron activates on adverbs ending in “-ly.”

    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
    \\
    -1.58
    such
    -1.37
    )\\
    -1.32
    )";
    -1.30
    1
    -1.28
    enumerate
    -1.22
     such
    -1.20
     unseren
    -1.20
    ,\\
    -1.20
     help
    -1.19
    POSITIVE LOGITS
    Dota
    1.38
     mesma
    1.30
     There
    1.26
     exacta
    1.16
     valamint
    1.13
     amiable
    1.13
    ibatkan
    1.12
     birkaç
    1.09
     around
    1.09
     くん
    1.09
    Activations Density 0.061%

    No Known Activations