© 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. 11607
    Prev
    Next
    INDEX
    Explanations

    straight lines or paths

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

    The neuron strongly activates on occurrences of the word “straight” (including in compounds like “straight‐through” or “straightener”).

    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
     The
    -2.88
     But
    -2.86
    ㉖
    -2.66
    sandalia
    -2.64
    皤
    -2.48
    まさ
    -2.41
     curioso
    -2.33
    簠
    -2.33
    鲠
    -2.33
     работал
    -2.27
    POSITIVE LOGITS
    酲
    3.55
    ～～
    3.34
    ции
    3.16
    谵
    3.02
    屜
    3.02
    脔
    2.98
    婓
    2.92
    愎
    2.88
    骜
    2.81
    ・・。
    2.73
    Activations Density 0.006%

    No Known Activations