© 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. 45722
    Prev
    Next
    INDEX
    Explanations

    acronyms and specific terms

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

    This neuron detects uppercase acronyms or initialisms (short sequences of capital letters).

    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
    what
    -2.78
    ський
    -2.53
    o
    -2.44
     penchant
    -2.44
    ︕
    -2.31
    m
    -2.30
     devono
    -2.23
     sembrano
    -2.20
    arraycopy
    -2.20
    this
    -2.20
    POSITIVE LOGITS
    稣
    2.94
    谖
    2.75
    荩
    2.73
    阄
    2.67
    </td>
    2.48
    đầm
    2.44
    acaktır
    2.44
    抔
    2.39
    tiembre
    2.38
    떳
    2.38
    Activations Density 0.094%

    No Known Activations