© 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. 34-GEMMASCOPE-RES-131K
    7. 116179
    Prev
    Next
    INDEX
    Explanations

    system documentation and code

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

    The neuron consistently fires on code‐style comment markers and license/disclaimer wording in source files (e.g. “//”, copyright or permission terms, and related phrases).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     VHS
    -0.74
     IPA
    -0.69
     Vertra
    -0.69
     America
    -0.68
     america
    -0.67
     Flex
    -0.67
    водства
    -0.66
    TestSuite
    -0.66
    StackNavigator
    -0.65
     ALT
    -0.64
    POSITIVE LOGITS
     schnelle
    0.79
     engen
    0.69
     Oldenburg
    0.68
    ZED
    0.65
     ネット
    0.65
    Upd
    0.65
    riders
    0.65
     courting
    0.64
    ANCING
    0.64
     Atwood
    0.64
    Activations Density 0.060%

    No Known Activations