© 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. 34084
    Prev
    Next
    INDEX
    Explanations

    we, you, our, your

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

    The neuron reliably flags the actual answer text in an FAQ (the explanatory or informational sentences) rather than the question lines.

    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
     this
    -1.16
     tonight
    -1.12
     bugün
    -1.04
    "$_
    -1.00
     cette
    -0.99
    pulseira
    -0.98
    isDone
    -0.96
    expectedResult
    -0.96
    sanitized
    -0.96
     dessa
    -0.94
    POSITIVE LOGITS
     our
    2.39
     you
    2.27
     your
    2.19
     we
    2.02
    Our
    1.92
    your
    1.59
    我們的
    1.56
    我们的
    1.50
    Your
    1.41
    我們
    1.39
    Activations Density 0.025%

    No Known Activations