© 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. 16710
    Prev
    Next
    INDEX
    Explanations

    feels like / noticed it

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

    The neuron fires on “by …​” phrases that mark the agent in a passive‐voice construction.

    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
     meille
    -1.61
     tekem
    -1.41
     stratég
    -1.41
     különböző
    -1.39
     célè
    -1.38
    enseignements
    -1.38
     kaksi
    -1.37
     verschillende
    -1.35
     énorm
    -1.35
     klicken
    -1.34
    POSITIVE LOGITS
    ).
    1.38
     except
    1.31
     to
    1.30
    .
    1.27
     or
    1.27
     at
    1.26
     in
    1.22
     on
    1.15
     and
    1.10
     with
    1.09
    Activations Density 0.009%

    No Known Activations