© 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. 79018
    Prev
    Next
    INDEX
    Explanations

    names and separators

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

    This neuron strongly activates on capitalized last names in email header fields.

    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
     and
    -1.45
     both
    -1.31
     for
    -1.21
     would
    -1.12
     which
    -1.05
    chemise
    -1.04
     their
    -1.03
     during
    -1.00
     with
    -0.99
     throughout
    -0.98
    POSITIVE LOGITS
    assuming
    1.16
    ,
    1.07
     nuage
    1.06
    Etape
    1.05
     можем
    1.05
     poate
    1.04
     piante
    1.02
     ancora
    0.98
    your
    0.97
     sommes
    0.97
    Activations Density 0.009%

    No Known Activations