© 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. 13759
    Prev
    Next
    INDEX
    Explanations

    Tomb raider, Coulomb interaction, Solar energy

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

    The neuron activates whenever the word “tomb” (or that exact substring) appears in the text.

    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
    
    -2.88
     dezelve
    -2.81
    鲀
    -2.64
    ѣмъ
    -2.58
    蹰
    -2.55
    菝
    -2.53
    戋
    -2.53
    ܴ
    -2.52
     glimpses
    -2.52
     zoude
    -2.50
    POSITIVE LOGITS
    s
    3.67
    I
    3.00
    ing
    2.97
    }$
    2.94
                    
    2.61
    –
    2.59
    <i>
    2.52
      
    2.33
     Those
    2.33
    𖥧
    2.27
    Activations Density 0.001%

    No Known Activations