© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 88
    Prev
    Next
    INDEX
    Explanations

    class definitions with extends or implements

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

    This neuron flags inheritance declarations in code (e.g. “class X < Y”, “extends”, “implements”).

    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
    そして
    -1.02
    viš
    -1.00
     $
    -0.97
    行事
    -0.97
     is
    -0.95
    serviceWorker
    -0.95
     dieser
    -0.93
    肴
    -0.93
    1
    -0.92
    two
    -0.90
    POSITIVE LOGITS
    ――――
    1.30
    ―――
    1.15
    Ἦ
    1.10
    敺
    1.09
    úrate
    1.09
    jeni
    1.09
     outono
    1.09
    Nevertheless
    1.08
    tells
    1.08
     Palest
    1.07
    Activations Density 0.007%

    No Known Activations