© 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. 120119
    Prev
    Next
    INDEX
    Explanations

    suggestive

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

    The neuron activates on various forms of the root “suggest,” flagging words that express suggestion or speculation (e.g. suggest, suggested, suggestive, suggestion).

    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
    -2.86
    ization
    -2.23
     we
    -2.17
    い
    -2.17
     новых
    -2.16
    篥
    -2.06
                
    -2.05
    ी
    -2.02
    躂
    -2.02
    ritsar
    -1.93
    POSITIVE LOGITS
    ጵ
    2.06
    jąca
    2.02
    g
    1.99
     Also
    1.91
    ！！！”
    1.88
    ánicas
    1.84
     reveal
    1.82
     Other
    1.80
    他现在
    1.79
    踌
    1.78
    Activations Density 0.021%

    No Known Activations