© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 64340
    Prev
    Next
    INDEX
    Explanations

    out of, outside, beyond, within

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

    The neuron strongly activates on the phrase “out of,” picking up the “out” token (and its following “of”) in “out of” constructions.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     PATIENT
    -1.43
     PAIN
    -1.34
     KNOWN
    -1.33
     mauva
    -1.31
    potentially
    -1.29
    certainly
    -1.28
    instead
    -1.27
    赑
    -1.27
     instead
    -1.26
    <0x17>
    -1.19
    POSITIVE LOGITS
     any
    1.88
     people
    1.84
     even
    1.70
     many
    1.67
     their
    1.63
     all
    1.57
     can
    1.51
     excessively
    1.48
     numerous
    1.46
     what
    1.45
    Activations Density 0.018%

    No Known Activations