© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 109141
    Prev
    Next
    INDEX
    Explanations

    introducing situations or facts

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

    The neuron strongly activates on demonstrative pronouns—especially “This”—when they appear at the start of a sentence.

    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
    volves
    -1.13
     assurances
    -0.96
     désir
    -0.92
     biedt
    -0.91
     ideals
    -0.91
     aspirations
    -0.91
    neté
    -0.91
    uur
    -0.90
     Requ
    -0.90
     purposes
    -0.89
    POSITIVE LOGITS
     fact
    2.19
     situation
    1.71
     lack
    1.66
     circumstance
    1.42
     Tatsache
    1.33
     makes
    1.31
     phenomenon
    1.30
     durumu
    1.24
    situation
    1.23
     facts
    1.20
    Activations Density 0.058%

    No Known Activations