© 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. 34-GEMMASCOPE-RES-131K
    7. 3458
    Prev
    Next
    INDEX
    Explanations

    exp

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

    The neuron responds to tokens that start with the letters “exp” (in any case) regardless of what follows.

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    </td>
    -1.27
    有不少
    -0.97
    生活中
    -0.94
    イラスト
    -0.94
     effects
    -0.93
     trennen
    -0.90
    」「
    -0.90
     bio
    -0.89
    此前
    -0.89
    早在
    -0.88
    POSITIVE LOGITS
     EXP
    1.30
     Bagian
    1.13
    EXP
    1.13
     Exped
    1.07
    ūras
    1.06
    exp
    1.04
    êmes
    1.03
    慑
    1.03
     exp
    0.98
    âneo
    0.97
    Activations Density 0.042%

    No Known Activations