© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 13886
    Prev
    Next
    INDEX
    Explanations

    because clauses

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

    The neuron detects first-person plural references (instances of “we” and related “we’re/we’ve” constructions).

    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
     clues
    -1.30
    тного
    -1.20
    elfde
    -1.16
     at
    -1.16
     decorativos
    -1.15
     one
    -1.15
     exacerbate
    -1.09
    eniem
    -1.09
    ється
    -1.08
     Lü
    -1.07
    POSITIVE LOGITS
    2
    1.41
     некоторых
    1.37
     otten
    1.36
     pretože
    1.36
     terutama
    1.35
    }.
    1.33
     incredibly
    1.26
     molte
    1.22
     protože
    1.21
    actually
    1.20
    Activations Density 0.058%

    No Known Activations