© 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. 102639
    Prev
    Next
    INDEX
    Explanations

    Mastering and gerunds

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

    The neuron detects “Read More” / “Continue Reading” style prompts (the call-to-action links with arrows) that invite the user to expand or continue the content.

    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
    0
    -2.73
    姈
    -2.33
     techniczne
    -2.25
    ⎙
    -2.16
    感じで
    -2.14
    趼
    -2.14
    二日
    -2.08
     mág
    -2.08
     για
    -2.06
    簾
    -2.05
    POSITIVE LOGITS
    E
    2.72
     disgruntled
    2.61
    O
    2.56
    ↵↵
    2.55
    秾
    2.53
    中国
    2.36
    >>();
    2.28
    to
    2.28
    她
    2.25
    냑
    2.25
    Activations Density 0.002%

    No Known Activations