© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 127403
    Prev
    Next
    INDEX
    Explanations

    Rahman and similar names

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

    The neuron detects occurrences of the substring “rahman” (in various spellings) in proper names.

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    </strong>
    -3.50
    </h3>
    -2.45
    </i>
    -2.42
    。“
    -2.19
    鹮
    -2.11
     of
    -2.08
    ﮑ
    -2.06
    visión
    -2.03
    恫
    -2.02
    遒
    -1.99
    POSITIVE LOGITS
    那個
    2.34
     Our
    2.20
    the
    2.13
    ’
    2.03
     équipée
    2.03
    ⚣
    1.95
     destinée
    1.95
     \\
    1.90
    當時
    1.84
     indep
    1.82
    Activations Density 0.006%

    No Known Activations