© 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. 81323
    Prev
    Next
    INDEX
    Explanations

    need to know

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

    This neuron detects direct second‐person addresses urging or promising information—phrases like “you need to know,” “you want to know,” or “everything you need to know.”

    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
     presidenta
    -0.93
     bringt
    -0.82
     Herrschaft
    -0.79
     wirkt
    -0.79
     batalla
    -0.79
     tárgy
    -0.77
     Acuerdo
    -0.76
    Ԥ
    -0.76
    轎
    -0.73
     lavado
    -0.73
    POSITIVE LOGITS
     know
    3.13
     to
    2.94
    know
    2.13
     knowing
    2.09
    Know
    2.08
     Know
    1.91
     знать
    1.80
    知道
    1.72
     weten
    1.71
     knows
    1.69
    Activations Density 0.045%

    No Known Activations