© 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. 34-GEMMASCOPE-RES-131K
    7. 99876
    Prev
    Next
    INDEX
    Explanations

    past participle after be

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

    The neuron flags modal and auxiliary verbs (like “can,” “may,” “be,” “grant,” “will”) commonly used in license and legal‐granting statements.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     being
    -1.23
    Leírás
    -1.13
    Takk
    -1.07
    推荐阅读
    -1.05
    Kategorie
    -1.05
     diren
    -1.05
    Už
    -1.05
    Pä
    -1.04
     adoptar
    -1.03
     españa
    -1.02
    POSITIVE LOGITS
     некоторы
    1.15
    ANDRO
    1.09
    cher
    1.06
    źdz
    1.06
    eight
    1.03
    ITEMS
    1.02
    I
    1.02
    token
    0.98
     situé
    0.96
    GONE
    0.95
    Activations Density 0.035%

    No Known Activations