© 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. 34-GEMMASCOPE-RES-131K
    7. 108148
    Prev
    Next
    INDEX
    Explanations

    bring forth my people

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

    This neuron responds to imperative or prophetic action verbs—especially first‐ or second‐person commands and proclamations (e.g. “Come,” “send,” “bring,” “declare,” “proclaim”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     we
    -1.23
    我们
    -0.96
     нам
    -0.94
    私たち
    -0.84
     our
    -0.84
     senhor
    -0.82
    咱们
    -0.79
    我們
    -0.79
     zdrowia
    -0.75
     Nguyễn
    -0.74
    POSITIVE LOGITS
     My
    3.50
    My
    3.09
     my
    2.70
     MY
    2.30
    my
    1.99
    getMy
    1.81
    MY
    1.80
     我的
    1.66
     Mijn
    1.57
    我的
    1.52
    Activations Density 0.054%

    No Known Activations