© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 40812
    Prev
    Next
    INDEX
    Explanations

    if you are

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

    The neuron fires strongly on the present‐tense “to be” forms “are” (and its contraction “’re”), especially when addressed to “you.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    屨
    -1.86
     same
    -1.75
    等は
    -1.57
    神
    -1.54
    threw
    -1.53
     большинстве
    -1.52
     seleccionados
    -1.50
     tremendous
    -1.50
    ⏑
    -1.49
    をしました
    -1.48
    POSITIVE LOGITS
     of
    2.66
     anderen
    1.91
    }>;
    1.73
     других
    1.69
     {
    
    1.68
    .}(
    1.66
    ">
    
    1.59
    ˃
    1.59
    ка
    1.55
     другими
    1.55
    Activations Density 0.021%

    No Known Activations