© 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. 44046
    Prev
    Next
    INDEX
    Explanations

    character creation and development

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

    The neuron is triggered by regular past‐tense verbs ending in “-ed.”

    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
     can
    -1.48
     السياس
    -1.37
     policies
    -1.31
    0
    -1.27
    żu
    -1.26
     sistema
    -1.26
     provider
    -1.25
    ἴ
    -1.24
     businesses
    -1.23
     methodologies
    -1.22
    POSITIVE LOGITS
    本章
    1.43
    一篇
    1.38
     who
    1.38
    estens
    1.35
     legyen
    1.34
    桀
    1.29
    }(),
    1.27
     whom
    1.27
     eredeti
    1.27
    WITHOUT
    1.26
    Activations Density 0.133%

    No Known Activations