© 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. 40547
    Prev
    Next
    INDEX
    Explanations

    here introducing context

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

    The neuron strongly activates on occurrences of the word “here” (in its various cases and positions).

    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
    橚
    -1.83
     ongeveer
    -1.75
    拶
    -1.67
     apparti
    -1.66
     preparados
    -1.63
     acuerdos
    -1.63
    콴
    -1.59
    毉
    -1.59
     rijden
    -1.58
     conectados
    -1.56
    POSITIVE LOGITS
    </strong>
    2.28
    at
    1.97
    s
    1.86
    ?’
    1.81
    ).
    1.57
        
    1.48
     by
    1.47
           
    1.47
     
    1.47
     ‘
    1.45
    Activations Density 0.010%

    No Known Activations