© 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. 34-GEMMASCOPE-RES-131K
    7. 103816
    Prev
    Next
    INDEX
    Explanations

    National guidelines

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

    This neuron picks out sequences of words that form formal section or paper titles—especially multiword, capitalized phrases (e.g. organization names or article titles).

    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
    Ima
    -0.74
     Ima
    -0.72
     inscriptions
    -0.69
     climax
    -0.68
     rego
    -0.68
    pepe
    -0.66
    满意
    -0.66
    公寓
    -0.66
    きゃ
    -0.66
     OECD
    -0.65
    POSITIVE LOGITS
     NICE
    1.52
    NICE
    1.17
    Nice
    1.14
    nice
    1.13
     nice
    1.13
     Nice
    0.98
     TMPro
    0.90
    technologies
    0.88
    technology
    0.84
     appraisal
    0.84
    Activations Density 0.029%

    No Known Activations