© 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. 10-GEMMASCOPE-RES-131K
    7. 15220
    Prev
    Next
    INDEX
    Explanations

    Rhode Island

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

    The neuron fires on occurrences of the geographic name “Rhode Island.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    </h4>
    -2.55
     französ
    -2.53
     said
    -2.45
    ↵
    -2.45
     eignen
    -2.39
    摃
    -2.36
    個人的
    -2.33
    which
    -2.30
    変な
    -2.28
     unterstützen
    -2.22
    POSITIVE LOGITS
     Française
    2.58
    蜴
    2.47
    鏐
    2.33
     あり
    2.30
    𝘽
    2.28
    ו
    2.28
    蹰
    2.28
     ヶ
    2.27
    🦁
    2.27
    er
    2.23
    Activations Density 0.006%

    No Known Activations