© 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. 13142
    Prev
    Next
    INDEX
    Explanations

    introduces alleged or questioned statements

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

    This neuron detects hedge or speculation markers, especially occurrences of “supposedly” (and its “supposed” variants).

    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
     '
    -3.00
    \
    -2.61
     doit
    -2.39
    )-
    -2.38
    e
    -2.38
    ''
    -2.30
     acti
    -2.14
    ଃ
    -2.09
     is
    -2.06
    でも
    -2.03
    POSITIVE LOGITS
     Ähn
    2.34
     They
    2.25
    וויק
    2.19
    が大
    2.16
     Furthermore
    2.16
     terwijl
    2.14
     Specifically
    2.06
    ጵ
    2.05
    柰
    2.00
     längere
    1.99
    Activations Density 0.002%

    No Known Activations