© 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. 776
    Prev
    Next
    INDEX
    Explanations

    shown by examples

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

    The neuron detects past-tense or past-participle verb forms (e.g. exemplified, manifested, demonstrated, seen).

    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
     eenige
    -1.10
    斡
    -0.94
    +
    -0.94
     dessus
    -0.93
    earch
    -0.91
    miento
    -0.90
    ९
    -0.90
    мы
    -0.90
     dû
    -0.89
    ENSES
    -0.89
    POSITIVE LOGITS
     in
    2.47
     through
    2.14
     when
    1.74
     especially
    1.64
     by
    1.57
     clearest
    1.55
     através
    1.54
     throughout
    1.45
     even
    1.42
     manifested
    1.40
    Activations Density 0.042%

    No Known Activations