© 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. 34-GEMMASCOPE-RES-131K
    7. 12210
    Prev
    Next
    INDEX
    Explanations

    MV prefix

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

    The neuron strongly activates on the two-letter uppercase sequence “MV” (and related uppercase bigrams like “VM”).

    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
     alcuni
    -0.85
     گرفتن
    -0.82
    一大
    -0.81
     Bühnen
    -0.76
    τρέ
    -0.75
     Tailor
    -0.74
    量的
    -0.72
    choenen
    -0.72
     Proced
    -0.71
     Bäume
    -0.71
    POSITIVE LOGITS
     MV
    1.16
    MV
    1.00
     mv
    0.95
    mv
    0.94
     première
    0.83
    vm
    0.80
     tej
    0.79
     thèse
    0.77
    added
    0.77
     Most
    0.75
    Activations Density 0.022%

    No Known Activations