© 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. 22-GEMMASCOPE-RES-131K
    7. 15437
    Prev
    Next
    INDEX
    Explanations

    relationship issues, spouses, leaving

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

    The neuron is keyed to clause-boundary markers—strongly responding to punctuation like commas, dashes, and to conjunctions or function words (e.g. “but,” “that”) that introduce or link subordinate clauses.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     ओवर
    -0.96
    ţele
    -0.91
     desper
    -0.85
    Доброго
    -0.84
    accordo
    -0.82
    Система
    -0.81
    Книга
    -0.80
    cenie
    -0.80
     управ
    -0.80
     購入
    -0.79
    POSITIVE LOGITS
     ungrateful
    1.00
     fonctionnalité
    0.96
     coldly
    0.94
     procédure
    0.88
     hurtful
    0.85
     Attitude
    0.84
     prefier
    0.84
    Ҷ
    0.84
     Loyalty
    0.84
     "";
    0.83
    Activations Density 0.032%

    No Known Activations