© 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. 34-GEMMASCOPE-RES-131K
    4. 98475
    Prev
    Next
    INDEX
    Explanations

    supported by grants or funding

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

    The neuron detects formal boilerplate or metadata tokens—things like funding acknowledgments (“supported”), license and copyright notices (“Distributed,” “Boost”), and code‐directive markers (“#define,” “#include,” “#endif”).

    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
    TKey
    -0.77
     UserDetails
    -0.74
     Spins
    -0.73
    Manhattan
    -0.72
     więcej
    -0.67
     اليه
    -0.67
    ográfica
    -0.66
    pluck
    -0.66
    ạ
    -0.65
    га
    -0.64
    POSITIVE LOGITS
    ressive
    0.74
    tômes
    0.73
     dian
    0.70
     german
    0.69
     Институ
    0.68
     Instituto
    0.68
     cliquer
    0.68
    Attempt
    0.67
     Wiki
    0.67
     horny
    0.67
    Activations Density 0.065%

    No Known Activations