© 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. 10-GEMMASCOPE-RES-131K
    7. 128586
    Prev
    Next
    INDEX
    Explanations

    conditional instructions

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

    The neuron fires on second-person instructional language—especially the pronoun “you” and the following base-form verbs in direct commands or guidance.

    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
    0
    -2.02
     駅前
    -1.82
    摀
    -1.81
     same
    -1.80
     craz
    -1.79
     incred
    -1.75
     AMAZING
    -1.73
     porque
    -1.73
     eſſ
    -1.72
    \
    -1.67
    POSITIVE LOGITS
     Offisielt
    1.71
    ≧
    1.70
     \
    1.63
     which
    1.63
    {§
    1.59
     of
    1.59
     September
    1.55
     have
    1.52
    Even
    1.51
    Hentet
    1.51
    Activations Density 0.035%

    No Known Activations