© 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. 10-GEMMASCOPE-RES-131K
    7. 12724
    Prev
    Next
    INDEX
    Explanations

    elseif or threefold increase

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

    This neuron responds most strongly to code-style conditional keywords (especially “elseif”) and related operators (e.g. the caret ^).

    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
    which
    -3.13
     oleh
    -2.41
    戆
    -2.27
    袮
    -2.27
     Which
    -2.23
     WHICH
    -2.22
    i
    -2.22
    zelfde
    -2.20
     كبيرة
    -2.16
     particolar
    -2.13
    POSITIVE LOGITS
    ↵↵
    2.61
    liſh
    2.59
    澳門
    2.31
    蹂
    2.30
    ),
    2.27
    ⸂
    2.27
     einfacher
    2.22
     schneller
    2.19
     trivi
    2.19
     für
    2.16
    Activations Density 0.001%

    No Known Activations