© 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. 10-GEMMASCOPE-RES-131K
    7. 119543
    Prev
    Next
    INDEX
    Explanations

    reporting findings after discoveries

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

    This neuron detects passive‐voice reporting or evidential phrases introducing scientific findings (e.g. “it was observed,” “it has been reported,” “it is shown,” “it has been estimated,” “it was revealed,” “it has just been announced”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     -
    -1.76
     its
    -1.64
    us
    -1.62
    its
    -1.59
    or
    -1.57
    andReturn
    -1.52
    et
    -1.49
    ManagedBean
    -1.48
    on
    -1.46
    ing
    -1.45
    POSITIVE LOGITS
     that
    3.27
     bahwa
    1.74
    ほとん
    1.63
     Pristup
    1.51
    赑
    1.48
     akrab
    1.48
    呿
    1.48
     Fazit
    1.46
    imbang
    1.46
     minuman
    1.44
    Activations Density 0.061%

    No Known Activations