© 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. 78402
    Prev
    Next
    INDEX
    Explanations

    available at

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

    The neuron fires on occurrences of the present‐tense linking verb “is.”

    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
     cartera
    -0.86
     ruolo
    -0.81
     Sortiment
    -0.79
     umgangssprach
    -0.77
    tellten
    -0.76
     controllare
    -0.75
    览
    -0.74
     Entsch
    -0.73
     marrone
    -0.73
    ControllerTest
    -0.73
    POSITIVE LOGITS
     at
    1.01
    geno
    0.88
     Σ
    0.83
    EventArgs
    0.82
     Pendleton
    0.80
     apartments
    0.77
     celebrations
    0.76
     Ас
    0.75
     grinding
    0.75
    filters
    0.75
    Activations Density 0.002%

    No Known Activations