© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 67075
    Prev
    Next
    INDEX
    Explanations

    clickbait headline

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

    The neuron is triggered by tokens that start new sections or headings (i.e. the first word of a paragraph or segment).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     Universitario
    -1.06
    🤓
    -1.05
    🍂
    -1.04
    》(
    -1.03
    😜
    -1.03
    🤨
    -1.02
    🥹
    -1.02
     reafon
    -1.02
    🤤
    -1.02
    😋
    -1.01
    POSITIVE LOGITS
     continúa
    1.16
     #
    1.16
     выглядит
    1.13
     sugerencias
    1.08
     executar
    1.08
     carregar
    1.07
     simplesmente
    1.07
     работают
    1.06
     únicamente
    1.05
    女朋友
    1.04
    Activations Density 0.001%

    No Known Activations