© 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. 93675
    Prev
    Next
    INDEX
    Explanations

    Quantification Hatem Minecraft Hi

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

    This neuron specializes in spotting capitalized tokens (names, organizations, code keywords) and numeric tokens (years, numbers).

    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
     contém
    -0.78
    zell
    -0.72
    ShortName
    -0.71
    сутствие
    -0.69
    lüğ
    -0.69
    étaient
    -0.67
    íu
    -0.66
    Uuid
    -0.66
    LOYD
    -0.66
    atischen
    -0.65
    POSITIVE LOGITS
     المرجع
    0.94
    breaks
    0.81
     PTI
    0.79
     filtres
    0.77
     creation
    0.77
     nő
    0.75
    ApiOperation
    0.74
     PM
    0.71
    mess
    0.71
     Tél
    0.70
    Activations Density 0.018%

    No Known Activations