© 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. 22-GEMMASCOPE-RES-131K
    7. 68619
    Prev
    Next
    INDEX
    Explanations

    award recipientindustry leader

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

    The neuron fires on prominent heading or title words—major topic or section‐header terms in the text.

    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
    ıyordu
    -1.05
     различ
    -1.03
     einzige
    -1.03
     विभिन्न
    -1.03
     dakika
    -1.02
     komplette
    -1.02
    」，
    -1.01
    我想
    -1.01
    她
    -0.99
    男人
    -0.99
    POSITIVE LOGITS
     is
    1.27
    真的好
    1.19
     слишком
    1.09
    _
    1.09
    闻言
    1.08
    はこちらから
    1.08
     boasting
    1.07
    捎
    1.07
     frío
    1.06
     samenwerking
    1.06
    Activations Density 0.229%

    No Known Activations