© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 12882
    Prev
    Next
    INDEX
    Explanations

    future or former states of being

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

    The neuron activates on words signaling future or conditional actions—especially auxiliary “would,” forms of “be,” and adverbs like “soon.”

    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
    )
    
    -2.00
    }),
    -1.91
    왑
    -1.90
    </td>
    -1.88
    лся
    -1.85
    </th>
    -1.79
    "]));
    -1.77
    </h4>
    -1.77
    茕
    -1.75
    ).
    -1.74
    POSITIVE LOGITS
    This
    2.28
     Understanding
    2.08
    i
    1.98
    勿論
    1.98
     and
    1.95
     tentunya
    1.94
     Watching
    1.92
     collaboration
    1.91
    و
    1.80
    𝘦
    1.80
    Activations Density 0.004%

    No Known Activations