© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49471
    Prev
    Next
    INDEX
    Explanations

    Loyalist and British sentiment

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

    The neuron principally activates on numeric tokens (especially multi‐digit numbers like years or counts).

    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
     Grot
    -0.78
    entid
    -0.69
    xy
    -0.68
     shotgun
    -0.67
     اشک
    -0.66
    索尼
    -0.66
     DPR
    -0.66
    народ
    -0.66
     coordenadas
    -0.66
     DPD
    -0.65
    POSITIVE LOGITS
     loyal
    2.53
     Loy
    2.36
     Loyal
    2.31
    Loy
    2.23
     British
    1.93
    British
    1.78
    loyal
    1.70
     Tory
    1.61
     Tories
    1.52
     british
    1.46
    Activations Density 0.052%

    No Known Activations