© 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. 34-GEMMASCOPE-RES-131K
    7. 48629
    Prev
    Next
    INDEX
    Explanations

    names of characters or people

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

    The neuron strongly activates on capitalized proper names (especially people’s names and notable entities).

    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
    __]
    -0.98
     Weltkrieg
    -0.90
     Writes
    -0.90
    ваете
    -0.88
    ప్
    -0.87
    seeable
    -0.86
     пишет
    -0.85
    是怎么回事
    -0.85
     bénéficiaire
    -0.84
    writes
    -0.83
    POSITIVE LOGITS
     character
    1.32
     lament
    1.21
     mention
    1.21
     dialogue
    1.20
     interactions
    1.15
    actable
    1.15
     interact
    1.13
     dialog
    1.08
     interacting
    1.08
     comment
    1.07
    Activations Density 0.028%

    No Known Activations