© 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. 62451
    Prev
    Next
    INDEX
    Explanations

    Teen Titans franchise

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

    The neuron strongly activates on uppercase acronyms, abbreviations, and numeric or punctuation-heavy tokens (e.g. H.I.V.E., issue numbers, capitalized codes).

    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
     مث
    -0.80
    ECs
    -0.75
     biodiversity
    -0.74
     Barre
    -0.72
     sm
    -0.71
     sk
    -0.71
     Einstein
    -0.70
    olis
    -0.69
     Ấ
    -0.69
    huis
    -0.69
    POSITIVE LOGITS
     Titans
    1.47
     Teen
    1.27
    Teen
    1.18
     titans
    1.14
     TIT
    1.13
     Trigon
    1.03
     nissan
    0.93
     Tamar
    0.92
    Tit
    0.91
     Krypto
    0.89
    Activations Density 0.024%

    No Known Activations