© 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. 34-GEMMASCOPE-RES-131K
    7. 108999
    Prev
    Next
    INDEX
    Explanations

    this followed by content noun

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

    The neuron strongly activates on the demonstrative “this,” i.e. instances of the word “this” pointing to a referenced item.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    昨日は
    -1.06
    (/^
    -1.02
     ersten
    -1.01
    これまで
    -0.98
    czyna
    -0.94
     haue
    -0.93
    😻
    -0.92
    
    -0.92
    otry
    -0.91
     plupart
    -0.91
    POSITIVE LOGITS
     article
    1.99
     recent
    1.80
     interview
    1.47
     YouTube
    1.40
     quote
    1.38
     reciente
    1.36
     earlier
    1.35
     comment
    1.35
     tweet
    1.35
     artículo
    1.30
    Activations Density 0.145%

    No Known Activations