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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 102700
    Prev
    Next
    INDEX
    Explanations

    Adrian and Mora related names

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

    The neuron activates on capitalized identifiers or proper nouns.

    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
    Ndr
    -2.75
    𖤣
    -2.73
    )’
    -2.66
    渽
    -2.61
    ᭝
    -2.55
    しちゃ
    -2.55
    玗
    -2.44
     铝
    -2.41
    ’,
    -2.38
    晛
    -2.38
    POSITIVE LOGITS
    ."
    3.88
    ing
    3.56
    the
    3.42
     '
    3.08
    \\
    3.02
    ]
    2.92
    4
    2.77
    to
    2.69
    牁
    2.56
    *
    2.50
    Activations Density 0.004%

    No Known Activations