© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 112176
    Prev
    Next
    INDEX
    Explanations

    names of colleges and people

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

    The neuron activates on specific proper names and identifiers—i.e. named entities such as people, places, organizations, or class/function 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
    '
    -3.89
    泺
    -3.11
    姤
    -2.63
    ⚋
    -2.59
     dezelve
    -2.42
    皞
    -2.39
    家伙
    -2.34
     permitan
    -2.28
    驺
    -2.27
    ꙰
    -2.23
    POSITIVE LOGITS
            
    3.02
                        
    2.98
    ];
    2.89
      
    2.84
    If
    2.73
                         
    2.64
    </td>
    2.58
    0
    2.48
                                   
    2.48
              
    2.45
    Activations Density 0.006%

    No Known Activations