© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 99893
    Prev
    Next
    INDEX
    Explanations

    pride in or on

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

    The neuron detects occurrences of “pride” (and its variants such as “prides,” “pride themselves,” etc.), flagging statements about taking or expressing pride.

    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
    mpagne
    -1.67
    睒
    -1.66
    家を
    -1.53
     BUT
    -1.48
     ("
    -1.46
     сум
    -1.45
    źdz
    -1.45
    棪
    -1.44
     ......
    -1.44
    ühnen
    -1.43
    POSITIVE LOGITS
    na
    1.59
     liknande
    1.57
    u
    1.57
     ويمكن
    1.48
    zo
    1.45
    first
    1.44
    垆
    1.44
     pierwszym
    1.41
    ok
    1.41
    es
    1.41
    Activations Density 0.004%

    No Known Activations