© 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. 75311
    Prev
    Next
    INDEX
    Explanations

    method calls after symbols

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

    The neuron mainly detects code punctuation used for member access or namespace resolution (e.g. “.” or “::”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     dando
    -1.47
     crucial
    -1.46
     magnific
    -1.36
     focuses
    -1.30
     sumptuous
    -1.28
     elegantly
    -1.20
     quirky
    -1.20
    cai
    -1.19
     hugely
    -1.17
     durante
    -1.16
    POSITIVE LOGITS
     and
    1.91
     as
    1.86
    When
    1.80
    Some
    1.63
    Every
    1.53
    Being
    1.48
     or
    1.44
    Many
    1.44
    Several
    1.43
    While
    1.41
    Activations Density 0.034%

    No Known Activations