© 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. 103688
    Prev
    Next
    INDEX
    Explanations

    examine or study

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

    The neuron flags research‐style investigation verbs (e.g. “examined,” “investigated,” “will examine”) that describe methods or study actions.

    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
    kker
    -1.34
    Ӝ
    -1.27
     самому
    -1.21
    状况
    -1.19
    以后
    -1.19
     Вікі
    -1.19
     seems
    -1.18
     queremos
    -1.16
    我们
    -1.13
     одна
    -1.13
    POSITIVE LOGITS
     to
    1.68
     how
    1.55
     ways
    1.33
     desmotiv
    1.32
    delà
    1.26
    raujo
    1.20
     tutur
    1.20
    umque
    1.19
    ursday
    1.19
     where
    1.19
    Activations Density 0.191%

    No Known Activations