© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 73509
    Prev
    Next
    INDEX
    Explanations

    thinking about yourself

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

    The neuron flags direct, second‐person–addressed advice or motivational/instructional phrases (you/your …).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     humeur
    -0.98
    irée
    -0.92
     încă
    -0.92
    simply
    -0.91
    Simply
    -0.91
    proken
    -0.91
     chapa
    -0.90
    تاریخ
    -0.88
     STABILITY
    -0.88
    diğimiz
    -0.88
    POSITIVE LOGITS
     your
    1.45
     yourself
    1.19
     mindset
    0.91
     L
    0.91
     AT
    0.90
     D
    0.88
     mentality
    0.88
     kwamba
    0.85
     ____
    0.85
     Treat
    0.83
    Activations Density 0.013%

    No Known Activations