© 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. 37923
    Prev
    Next
    INDEX
    Explanations

    my + possession

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

    The neuron fires on hardware‐ and brand‐related terms (model numbers, manufacturer names, specs, etc.).

    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
     you
    -1.09
    ibatis
    -1.08
     your
    -1.02
     models
    -0.95
     silueta
    -0.94
     estatua
    -0.94
     posteriore
    -0.94
    =="")
    -0.93
     imágen
    -0.93
    ález
    -0.93
    POSITIVE LOGITS
     my
    1.29
     wife
    1.15
     velho
    1.09
     old
    1.08
     vieux
    1.06
     vieille
    1.06
     MacBook
    1.05
     Wife
    1.02
    ROUT
    0.99
     iPhone
    0.98
    Activations Density 0.205%

    No Known Activations