© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99198
    Prev
    Next
    INDEX
    Explanations

    places ending in side

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

    The neuron activates strongly on words ending with the suffix “side.”

    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
     renfer
    -0.87
     apparaître
    -0.86
     laiko
    -0.85
     ZR
    -0.80
     voi
    -0.80
    稣
    -0.78
     &
    -0.78
    殓
    -0.74
     sidelines
    -0.74
     sidelined
    -0.73
    POSITIVE LOGITS
     assistance
    1.04
    hamed
    0.88
     chats
    0.88
     muncul
    0.83
    谘
    0.82
    tação
    0.82
     at
    0.82
    نائ
    0.81
     تجمعات
    0.80
    暴露
    0.80
    Activations Density 0.020%

    No Known Activations