© 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. 22-GEMMASCOPE-RES-131K
    7. 129119
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on occurrences of the demonstrative “This” (or “this”)—especially at the start of comment or documentation sentences.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    "This" followed by description

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    iaomi
    -1.20
    ようですが
    -1.13
     innych
    -1.13
    autogui
    -1.12
     his
    -1.12
    ッセ
    -1.11
     بسیار
    -1.10
     欣赏
    -1.09
     paroisse
    -1.08
    Beskrivning
    -1.07
    POSITIVE LOGITS
     will
    1.33
     Pilipinas
    1.25
    section
    1.18
     Octobre
    1.15
    了一会儿
    1.13
    usd
    1.13
     {$\
    1.09
    ってください
    1.06
    😤
    1.05
     section
    1.04
    Activations Density 0.081%

    No Known Activations