© 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. 32728
    Prev
    Next
    INDEX
    Explanations

    collective entities

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

    The neuron spikes on common plural nouns.

    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
     مثل
    -1.11
     solchen
    -1.08
     or
    -0.98
     relacionadas
    -0.97
     its
    -0.92
     devam
    -0.91
     verses
    -0.90
     Larger
    -0.90
    нению
    -0.90
    他の
    -0.90
    POSITIVE LOGITS
     themselves
    3.20
     of
    1.90
    themselves
    1.88
     that
    1.49
     mentioned
    1.42
     we
    1.41
     сами
    1.34
     stessi
    1.31
     who
    1.30
    mentioned
    1.27
    Activations Density 0.241%

    No Known Activations