© 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. 6716
    Prev
    Next
    INDEX
    Explanations

    desires, wishes, and preferences

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

    The neuron fires strongly on personal and indefinite pronouns (especially “you,” “they,” “anything,” etc.) that refer to agents or readers.

    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
    utta
    -0.93
    Gizmos
    -0.90
    heits
    -0.86
    }=\
    -0.84
    чах
    -0.84
    asz
    -0.84
    lacement
    -0.84
     Kanal
    -0.83
     &___
    -0.83
    ços
    -0.82
    POSITIVE LOGITS
     pleases
    2.44
     please
    2.33
     like
    2.14
     pleased
    2.03
     Please
    1.95
     likes
    1.93
    Please
    1.88
     choose
    1.80
     wish
    1.70
     want
    1.63
    Activations Density 0.023%

    No Known Activations