© 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. 68855
    Prev
    Next
    INDEX
    Explanations

    for users to

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

    The neuron strongly activates on words naming or referring to people or groups (e.g. pronouns like “him,” “us,” and role‐oriented nouns like “user,” “owners,” “laboratories”).

    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
     sandalias
    -1.06
     utilisée
    -1.05
     strengthened
    -1.03
     exitoso
    -1.02
    Berat
    -1.02
     む
    -1.02
    Awal
    -1.02
     merec
    -1.00
     automóviles
    -1.00
     cómodo
    -1.00
    POSITIVE LOGITS
     to
    3.06
     чтобы
    1.48
     who
    1.40
    เพื่อ
    1.11
     když
    1.09
     щоб
    1.02
    のために
    1.01
     чтоб
    1.00
     ול
    0.99
    以便
    0.98
    Activations Density 0.048%

    No Known Activations