© 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. 129662
    Prev
    Next
    INDEX
    Explanations

    given that

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

    The neuron strongly activates on the subordinating conjunction “that” (the token “that” introducing a clause).

    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
    1
    -1.89
    _
    -1.85
    </td>
    -1.80
    }
    -1.80
    She
    -1.77
     }}$
    -1.76
     the
    -1.74
     frucht
    -1.73
    </h5>
    -1.69
    3
    -1.66
    POSITIVE LOGITS
    rinology
    1.79
    跸
    1.76
    一会
    1.75
    WAUKEE
    1.68
    谞
    1.66
     própri
    1.60
    DALE
    1.60
    
    1.59
    桧
    1.59
     yetu
    1.59
    Activations Density 0.009%

    No Known Activations