© 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. 77609
    Prev
    Next
    INDEX
    Explanations

    minecraft related terms

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

    The neuron is primarily activating on numeric tokens—i.e. sequences of digits (numbers) in the text.

    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
     μα
    -0.80
    清水
    -0.75
     Talent
    -0.73
    pacs
    -0.73
    Script
    -0.71
    ('=
    -0.71
    country
    -0.70
    allclose
    -0.70
    Guid
    -0.68
    beer
    -0.68
    POSITIVE LOGITS
     łóż
    0.85
     hyp
    0.85
    高兴
    0.81
    拍攝
    0.78
     Hyp
    0.77
    ķ
    0.76
    krish
    0.76
    лися
    0.75
     oxígeno
    0.75
     MCA
    0.74
    Activations Density 0.010%

    No Known Activations