© 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. 54233
    Prev
    Next
    INDEX
    Explanations

    adult education

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

    The neuron fires on uppercase alphanumeric tokens—especially project codes, acronyms, and numbers.

    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
    Итог
    -0.92
    frutar
    -0.73
    లు
    -0.72
     wisatawan
    -0.70
    SECON
    -0.69
    Важно
    -0.69
    leggings
    -0.69
     함께
    -0.68
     বি
    -0.66
     communicated
    -0.66
    POSITIVE LOGITS
    Adult
    1.89
     adult
    1.73
     Adult
    1.71
     adults
    1.62
    adult
    1.59
     Adults
    1.58
     lifelong
    1.55
    Adults
    1.55
     learner
    1.45
     ADULT
    1.38
    Activations Density 0.011%

    No Known Activations