© 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. 128105
    Prev
    Next
    INDEX
    Explanations

    actions and states following prepositions

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

    The neuron fires on words that express or describe collective/group actions, sentiments, or permissions (e.g. public opinion, mass behavior, what a populace will or won’t do).

    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
     then
    -1.80
     such
    -1.45
    τως
    -1.30
    کنند
    -1.26
     bieden
    -1.24
     pembeli
    -1.23
    such
    -1.23
    lusconi
    -1.21
     there
    -1.20
    طقة
    -1.17
    POSITIVE LOGITS
    Their
    1.20
     gena
    1.20
    尽管
    1.20
     baden
    1.19
    「
    1.16
    tired
    1.16
     Their
    1.15
    م
    1.14
    当我
    1.14
    ֹא
    1.12
    Activations Density 0.101%

    No Known Activations