© 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. 34-GEMMASCOPE-RES-131K
    7. 107873
    Prev
    Next
    INDEX
    Explanations

    dealing with situations and consequences

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

    The neuron fires on occurrences of the verb “deal” when used in constructions like “dealing with” or “dealt with.”

    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
    音が
    -1.12
     barring
    -0.91
    
    -0.89
     partire
    -0.84
    神
    -0.83
     coarsely
    -0.82
    榨
    -0.82
    Цент
    -0.81
     kosmety
    -0.80
    Personendaten
    -0.79
    POSITIVE LOGITS
     Dealing
    1.88
    Dealing
    1.87
     dealt
    1.73
     deal
    1.69
    dealing
    1.58
     Deal
    1.52
     dealing
    1.49
    deal
    1.31
     DEAL
    1.29
     deals
    1.28
    Activations Density 0.015%

    No Known Activations