© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 72080
    Prev
    Next
    INDEX
    Explanations

    Seismic shifts, South Africa, Google Chrome

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

    The neuron detects long, dense alphanumeric strings (including “+/=” characters) characteristic of Base64‐encoded data such as cryptographic keys.

    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
    ſſen
    -2.45
    鸲
    -2.19
    鵙
    -2.19
    вгений
    -2.17
    罽
    -1.95
    糴
    -1.94
     bénéficiaire
    -1.94
     obligación
    -1.92
     movilidad
    -1.89
     $^{\
    -1.85
    POSITIVE LOGITS
    ↵↵
    2.41
    </strong>
    1.88
     THE
    1.85
    We
    1.75
     thing
    1.62
     ‘
    1.61
    9
    1.59
     To
    1.57
    ING
    1.55
    se
    1.52
    Activations Density 0.019%

    No Known Activations