© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 73601
    Prev
    Next
    INDEX
    Explanations

    in this manner/way/kind

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

    The neuron detects formal method‐introducing phrases—especially demonstrative manner expressions like “in this manner,” “in this way,” or “in that manner.”

    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
     which
    -1.57
     avrebbe
    -1.45
     for
    -1.40
     nup
    -1.27
     veniva
    -1.26
    reiches
    -1.25
     grama
    -1.25
     iveco
    -1.24
     veik
    -1.21
     to
    -1.20
    POSITIVE LOGITS
     asistentes
    1.47
     sucede
    1.23
    優しく
    1.23
     productores
    1.23
     Николай
    1.20
    dienne
    1.18
    жмите
    1.18
    WriteAttribute
    1.17
     kobieta
    1.17
     '
    1.16
    Activations Density 0.051%

    No Known Activations