© 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. 47158
    Prev
    Next
    INDEX
    Explanations

    account status

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

    The neuron detects occurrences of the word “account” (i.e. references to account-related terms).

    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
    自己的
    -1.11
    1
    -1.00
    身体
    -0.91
    戻る
    -0.89
     встреча
    -0.88
     lernen
    -0.88
    自分の
    -0.86
    9
    -0.86
    重重
    -0.85
     棒
    -0.85
    POSITIVE LOGITS
     created
    1.15
    上司
    1.13
     holder
    1.13
    ancy
    1.10
     holders
    1.03
     with
    1.03
     linked
    1.01
    הא
    0.99
     cread
    0.98
     Agreg
    0.98
    Activations Density 0.043%

    No Known Activations