© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 11173
    Prev
    Next
    INDEX
    Explanations

    things that are not right

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

    The neuron specifically detects occurrences of the word “undue” (marking something excessive or unwarranted).

    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
     From
    -2.20
     Another
    -2.14
     usai
    -2.11
    蠵
    -2.06
     Then
    -2.03
     caneca
    -2.00
     passaggio
    -1.99
     Three
    -1.95
    土曜
    -1.94
    蔼
    -1.94
    POSITIVE LOGITS
    e
    2.16
    の姿
    2.02
    t
    1.93
    jenige
    1.89
     это
    1.89
    啬
    1.88
    ка
    1.81
    ↵↵
    1.80
     possam
    1.77
    amp
    1.75
    Activations Density 0.002%

    No Known Activations