© 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. 40215
    Prev
    Next
    INDEX
    Explanations

    punctuation followed by common words

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

    The neuron selectively activates on the token “as” when it’s used to introduce definitions, identifications, or comparisons (e.g. “is known as,” “included as,” “characterizes … as”).

    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
     in
    -1.53
     for
    -1.42
     on
    -1.41
     like
    -1.25
    _{\
    -1.15
    Semoga
    -1.09
     throughout
    -1.07
     some
    -1.06
     were
    -1.06
     /
    -1.05
    POSITIVE LOGITS
     menant
    1.35
     zove
    1.30
     tavo
    1.30
     grafica
    1.28
     écouter
    1.28
     véhic
    1.28
     réinitial
    1.27
     lavable
    1.27
     mengel
    1.27
     entraîner
    1.27
    Activations Density 0.174%

    No Known Activations