© 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. 87133
    Prev
    Next
    INDEX
    Explanations

    asking for thoughts

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

    The neuron primarily detects reader-directed opinion questions (e.g. “what do you think,” “we want to hear what you think,” etc.).

    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
     varför
    -0.83
    了出去
    -0.78
     pouze
    -0.74
     conservatism
    -0.73
     Warsaw
    -0.73
     melatonin
    -0.73
     Татьяна
    -0.71
    phrine
    -0.70
     khoản
    -0.70
    汚れ
    -0.70
    POSITIVE LOGITS
     think
    3.44
     thinks
    2.69
    think
    2.39
    Think
    2.34
     Think
    2.27
     thought
    2.16
     thoughts
    1.78
     thinking
    1.77
     nghĩ
    1.67
     THINK
    1.63
    Activations Density 0.020%

    No Known Activations