© 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. 10-GEMMASCOPE-RES-131K
    7. 72195
    Prev
    Next
    INDEX
    Explanations

    I'm interested

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

    This neuron detects English contraction suffix tokens (e.g. ’m, ’ve, ’ll, ’re) attached to pronouns.

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    0
    -2.98
     for
    -2.53
    *
    -2.48
    8
    -2.39
    3
    -2.33
    9
    -2.33
    Before
    -2.06
    After
    -2.05
     and
    -2.03
    When
    -2.03
    POSITIVE LOGITS
    廰
    2.44
    埽
    2.31
    犼
    2.27
    ଢ
    2.20
    ✱
    2.16
     dì
    2.11
    籥
    2.09
     ſaid
    2.02
     vê
    2.02
    attutto
    2.02
    Activations Density 0.006%

    No Known Activations