© 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. 37859
    Prev
    Next
    INDEX
    Explanations

    big fan of

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

    This neuron fires on first-person self-statements expressing personal preference or enthusiasm (e.g. “I’m a big fan,” “I have a thing for,” “I’m a sucker for”).

    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
    其他的
    -0.90
     possible
    -0.85
     distinction
    -0.84
     خواست
    -0.84
    なりに
    -0.83
     registr
    -0.83
    個人的
    -0.82
     other
    -0.82
    Ár
    -0.81
     desirable
    -0.81
    POSITIVE LOGITS
     proponent
    1.41
     believer
    1.38
     advocate
    1.25
     believe
    1.06
     believers
    1.05
     proponents
    1.05
    big
    0.96
     advocates
    0.95
     advocating
    0.93
     sucker
    0.91
    Activations Density 0.026%

    No Known Activations