© 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. 110908
    Prev
    Next
    INDEX
    Explanations

    assumptions about subsequent versions

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

    The neuron detects named entities and other proper nouns (e.g. titles of publications, place names, organizations).

    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
     colheres
    -0.80
    tisan
    -0.80
     dovrebbero
    -0.78
     APPROACH
    -0.74
     maximal
    -0.73
     fokus
    -0.73
    sandal
    -0.73
    textt
    -0.73
    approche
    -0.73
     adatt
    -0.73
    POSITIVE LOGITS
     assumptions
    1.10
     assumed
    1.04
     assumption
    1.01
     assume
    0.94
    Assume
    0.90
    assumed
    0.88
     Assumptions
    0.86
    assume
    0.85
     assumes
    0.84
     Assume
    0.83
    Activations Density 0.013%

    No Known Activations