© 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. 65324
    Prev
    Next
    INDEX
    Explanations

    years, bedroom, organs, honestly

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

    The neuron strongly activates on personal pronouns (e.g. you, they, we, our) throughout the text.

    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
     adresses
    -1.23
     墊
    -1.23
    horabuena
    -1.22
    pherds
    -1.15
     spons
    -1.14
    アンサー
    -1.14
     fué
    -1.11
    BURN
    -1.10
    ¹,
    -1.09
    felizmente
    -1.09
    POSITIVE LOGITS
     
    1.05
     so
    1.01
     |
    0.99
     f
    0.98
    . 
    0.98
     +
    0.98
     F
    0.96
               
    0.95
                    
    0.94
     M
    0.94
    Activations Density 0.029%

    No Known Activations