© 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. 70103
    Prev
    Next
    INDEX
    Explanations

    named selected awarded ranked listed

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

    The neuron strongly fires on passive‐voice award or recognition statements (e.g. “was named,” “has been recognized”).

    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
    famous
    -0.88
    Setelah
    -0.85
    satunya
    -0.85
    ロナ
    -0.85
    demik
    -0.83
    inguém
    -0.83
    Извест
    -0.83
     افراد
    -0.82
    pandas
    -0.82
    ತಿ
    -0.82
    POSITIVE LOGITS
     named
    4.59
    named
    2.91
    Named
    2.67
     Named
    2.45
     selected
    2.41
     voted
    2.38
     awarded
    2.30
     name
    2.25
     наз
    2.19
     chosen
    2.14
    Activations Density 0.074%

    No Known Activations