© 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. 22-GEMMASCOPE-RES-131K
    7. 72212
    Prev
    Next
    INDEX
    Explanations

    names preceded by Brad

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

    The neuron activates on personal 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_22/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
    蜮
    -2.58
    𓆜
    -2.44
    鉝
    -2.31
    秝
    -2.27
     ordinarily
    -2.25
    几个月
    -2.17
    出了一
    -2.17
    prnewswire
    -2.16
    晅
    -2.16
    骜
    -2.14
    POSITIVE LOGITS
    5
    3.19
    1
    3.08
    ↵↵
    3.08
    2
    2.86
    7
    2.67
    6
    2.61
    </i>
    2.59
    to
    2.50
                        
    2.50
    a
    2.44
    Activations Density 0.012%

    No Known Activations