© 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. 28150
    Prev
    Next
    INDEX
    Explanations

    regarding the procedures

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

    The neuron fires on third-person plural agent references—especially pronouns like “they/their” (and related gerundive verbs like “making,” “providing”).

    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
     Words
    -0.84
     täv
    -0.82
     לעשות
    -0.81
    ēd
    -0.80
     sätt
    -0.80
    u
    -0.77
     omfatt
    -0.77
     BEM
    -0.76
     största
    -0.76
     beitragen
    -0.75
    POSITIVE LOGITS
     yourself
    1.05
     you
    1.04
     patients
    0.98
     your
    0.91
     clients
    0.91
     galinha
    0.90
     polska
    0.90
     seleccion
    0.88
     audiences
    0.87
    expectation
    0.86
    Activations Density 0.165%

    No Known Activations