© 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. 86815
    Prev
    Next
    INDEX
    Explanations

    Luis Mariano or Come Fly

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

    The neuron specifically detects the surname “Mardhekar,” activating on the “Mard” portion of that name.

    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
    \
    -2.80
     \\
    -2.14
     была
    -2.02
    ﺅ
    -2.00
     l
    -1.98
    н
    -1.95
    是否有
    -1.93
     dichos
    -1.91
    Compared
    -1.89
    神
    -1.89
    POSITIVE LOGITS
    鋨
    2.53
    琑
    2.48
    獁
    2.11
    猡
    2.08
    騭
    2.06
    mord
    2.05
    泺
    1.99
    genheiten
    1.92
    ⟯
    1.91
     車場
    1.90
    Activations Density 0.000%

    No Known Activations