© 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. 68579
    Prev
    Next
    INDEX
    Explanations

    dep state, press, depart, depress

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

    The neuron consistently fires on the token “Dep” (i.e. the “Dep” substring at the start of words).

    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
    </h3>
    -2.83
    ."
    -2.67
    as
    -2.47
    呖
    -2.45
    ).
    -2.45
    ET
    -2.23
    AN
    -2.11
    辚
    -2.11
    ↵↵
    -2.08
    this
    -2.06
    POSITIVE LOGITS
     "...
    2.69
    祘
    2.67
    虽然
    2.31
     $^{
    2.30
    rozco
    2.28
    澌
    2.28
    »։
    2.23
     While
    2.23
    在我的
    2.19
    ...?
    2.16
    Activations Density 0.008%

    No Known Activations