© 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. 10-GEMMASCOPE-RES-131K
    7. 19151
    Prev
    Next
    INDEX
    Explanations

    Sussex County Trail coronerbundes ministerium

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

    The neuron strongly activates on occurrences of “Sussex” (especially in “Sussex County”).

    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
    u
    -2.80
    慙
    -2.28
    ことなく
    -2.25
    صورة
    -2.25
    。
    -2.23
    棐
    -2.19
    }
    -2.14
    ⇹
    -2.14
    甡
    -2.13
    
    -2.05
    POSITIVE LOGITS
    s
    2.52
    </sup>
    2.33
    ſu
    2.28
    みよう
    2.19
     ſta
    2.16
    ኻ
    2.13
    isation
    2.13
    ra
    2.08
    但她
    2.05
    1.98
    Activations Density 0.003%

    No Known Activations