© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 13662
    Prev
    Next
    INDEX
    Explanations

    people and their connections

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

    The neuron fires on passages describing workplace economic hardship—mentions of someone’s place of employment, layoffs, and related financial worries.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     my
    -1.81
     or
    -1.55
     our
    -1.45
     we
    -1.23
     meiner
    -1.11
     I
    -1.09
    واصل
    -1.08
     meines
    -1.06
     моих
    -1.04
    ,
    -1.02
    POSITIVE LOGITS
     his
    2.02
     himself
    1.48
     suoi
    1.43
    himself
    1.41
     she
    1.28
    っていました
    1.22
     he
    1.21
     его
    1.14
     themselves
    1.13
     자신
    1.13
    Activations Density 0.049%

    No Known Activations