© 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. 100082
    Prev
    Next
    INDEX
    Explanations

    Dominion and RPM

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

    The neuron is triggered by capitalized proper names and acronyms (named entities) in the text.

    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
    鉏
    -2.70
     bedeckt
    -2.69
    を活用
    -2.64
     ͡
    -2.61
    韡
    -2.59
     sprüche
    -2.55
    囯
    -2.47
    苳
    -2.45
    踌
    -2.44
    ről
    -2.41
    POSITIVE LOGITS
    er
    3.44
     tetapi
    3.42
        
    3.06
     But
    3.03
     После
    2.70
     αλλά
    2.69
     After
    2.67
     लेकिन
    2.56
    ，“
    2.55
     “
    2.53
    Activations Density 0.020%

    No Known Activations