© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 89737
    Prev
    Next
    INDEX
    Explanations

    Versatility, verse, transverse

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

    This neuron responds to tokens containing the character sequence “vers,” i.e. words or names with “vers” in them.

    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
     zw
    -0.75
    Boots
    -0.73
    穢
    -0.73
     swans
    -0.73
     continuidad
    -0.72
    犷
    -0.72
    ANES
    -0.71
     серви
    -0.71
     RIGHTS
    -0.71
    Scripts
    -0.70
    POSITIVE LOGITS
     VERS
    0.92
    atiles
    0.92
     versa
    0.91
    Vers
    0.89
     vers
    0.87
     Vers
    0.82
    ÍSTICAS
    0.81
     Versace
    0.81
     luis
    0.80
    atility
    0.79
    Activations Density 0.021%

    No Known Activations