© 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. 22-GEMMASCOPE-RES-131K
    7. 39656
    Prev
    Next
    INDEX
    Explanations

    people associated with actions or states

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

    The neuron strongly activates on proper names of individual people.

    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
     I
    -1.16
     /
    -1.11
     should
    -0.98
    Nội
    -0.95
    #%%
    -0.95
     piacere
    -0.90
     allarg
    -0.90
    冼
    -0.88
     Особенно
    -0.88
    Czym
    -0.88
    POSITIVE LOGITS
     who
    1.34
     in
    1.27
    weren
    1.19
    beria
    1.17
    ⎤
    1.13
    两天
    1.09
    igth
    1.07
    ELTS
    1.06
     který
    1.06
     at
    1.06
    Activations Density 0.068%

    No Known Activations