© 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. 34-GEMMASCOPE-RES-131K
    7. 3100
    Prev
    Next
    INDEX
    Explanations

    names ending in -us

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

    The neuron fires on tokens containing the sequence “us,” especially proper names or words ending in “us.”

    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
    彼らの
    -0.83
    iya
    -0.80
     unmatched
    -0.76
    つづく
    -0.76
     eyesight
    -0.73
    余談
    -0.72
    ians
    -0.72
     larger
    -0.71
    為に
    -0.71
    ets
    -0.70
    POSITIVE LOGITS
    ses
    1.24
     Maximus
    0.95
    sy
    0.94
    sa
    0.91
    否
    0.88
    сь
    0.85
     Rex
    0.82
    وي
    0.82
     accordion
    0.81
    ড
    0.81
    Activations Density 0.085%

    No Known Activations