© 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. 22-GEMMASCOPE-RES-131K
    7. 71968
    Prev
    Next
    INDEX
    Explanations

    function or method calls using parentheses

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

    The neuron fires strongly on the punctuation that opens a function or generic declaration—i.e. the “(” or angle‐bracket tokens marking the start of parameter lists or type parameters.

    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
    ッピー
    -1.08
     otthon
    -1.05
     hadden
    -1.05
     ardından
    -1.05
     dirigentes
    -1.04
     désormais
    -1.03
     jabón
    -1.03
     COMPOUNDS
    -1.02
     紫色
    -1.02
     sólidos
    -1.02
    POSITIVE LOGITS
    3
    1.22
    8
    1.17
    5
    1.16
     or
    1.14
    7
    1.09
    2
    1.09
     only
    1.03
    4
    1.02
    ﻢ
    0.97
    6
    0.96
    Activations Density 0.004%

    No Known Activations