© 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. 67887
    Prev
    Next
    INDEX
    Explanations

    middleware, handler, chain

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

    The neuron fires on tokens that look like programming‐language identifiers and keywords (e.g. class, Delegate, next, intercept), i.e. it’s spotting code syntax.

    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
     chansons
    -1.00
    #(
    -0.98
     ἐν
    -0.96
    子さん
    -0.95
     ditambah
    -0.94
     schwarze
    -0.92
     repertorio
    -0.92
    Эзо
    -0.92
    Memoria
    -0.90
    気がする
    -0.89
    POSITIVE LOGITS
     Moines
    1.01
    ælde
    0.97
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.95
    breitung
    0.93
    ↵↵↵↵↵↵↵↵↵↵↵↵
    0.92
     様子
    0.92
    бражение
    0.91
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.90
     uitvo
    0.90
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.90
    Activations Density 0.007%

    No Known Activations