© 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. 38210
    Prev
    Next
    INDEX
    Explanations

    proposing or suggesting something

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

    The neuron fires on tokens typical of formal or academic passive‐voice constructions and related nominalizations—e.g. auxiliaries like “is,” “has,” “been” and passive/nominalized verbs such as “proposed,” “shown,” “realization.”

    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
     legenda
    -1.02
    hibit
    -0.95
    руппа
    -0.93
    اصيل
    -0.88
     biber
    -0.86
     rotu
    -0.86
    expects
    -0.85
    ിച്ച
    -0.84
    ↗
    -0.84
    confirmed
    -0.83
    POSITIVE LOGITS
     suggested
    6.19
     proposed
    5.81
     suggestion
    5.78
     suggest
    5.69
     suggestions
    5.66
     propose
    5.31
     proposal
    5.09
     suggesting
    5.06
     proposing
    4.88
     proposes
    4.81
    Activations Density 0.254%

    No Known Activations