© 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. 90289
    Prev
    Next
    INDEX
    Explanations

    Ricky followed by names/titles

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

    The neuron detects the specific proper name “Ricky.”

    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
    ي
    -3.06
    י
    -2.94
    ')
    -2.83
    ).
    -2.59
    ى
    -2.58
    ],
    -2.48
    }
    -2.45
    烔
    -2.44
    </
    -2.42
     "
    -2.36
    POSITIVE LOGITS
    er
    3.02
     them
    2.72
    N
    2.58
    自己的
    2.47
    ⟐
    2.45
    。“
    2.30
     adil
    2.30
    Bele
    2.28
    StoryboardSegue
    2.28
    t
    2.27
    Activations Density 0.012%

    No Known Activations