© 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. 10-GEMMASCOPE-RES-131K
    7. 40787
    Prev
    Next
    INDEX
    Explanations

    prerequisites and requirements

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

    The neuron detects mentions of prerequisites or preconditions (e.g. “Prerequisites,” “Before you start,” “preconditions”).

    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
     was
    -1.43
     Initially
    -1.35
    Such
    -1.27
     Particularly
    -1.27
     There
    -1.27
     more
    -1.25
     大
    -1.23
     Providing
    -1.23
     สำหรับ
    -1.23
     how
    -1.21
    POSITIVE LOGITS
    cestor
    1.32
    耵
    1.32
     aſ
    1.31
     druge
    1.30
     vectorstock
    1.27
     kommunen
    1.27
    蚴
    1.27
     thingy
    1.25
    HEARING
    1.25
    ilados
    1.24
    Activations Density 0.103%

    No Known Activations