© 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. 83638
    Prev
    Next
    INDEX
    Explanations

    confidentiality and confidence

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

    The neuron fires on any token containing the letter sequence “fi” (e.g. in “confit,” “config,” “confidence,” “fit,” etc.).

    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
     falschen
    -2.34
     selben
    -2.28
     Когда
    -2.28
    徇
    -2.25
     kleinen
    -2.23
     echten
    -2.22
     kurzen
    -2.20
     sogenannten
    -2.19
     maravillosa
    -2.17
     häufigsten
    -2.05
    POSITIVE LOGITS
    "--
    2.38
    ーズン
    2.22
    ſſel
    2.20
    EDING
    2.09
     Organizador
    2.09
    栊
    2.03
    佧
    2.03
    ".
    2.00
    見る
    1.97
    "...
    1.96
    Activations Density 0.005%

    No Known Activations