© 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. 58528
    Prev
    Next
    INDEX
    Explanations

    hot and subsequent terms

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

    The neuron primarily activates on the capitalized word “Hot” when it appears in titles or as part of proper names.

    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
    vigil
    -0.79
    }}}\
    -0.79
     subtly
    -0.75
     Gottesdienst
    -0.74
    ensión
    -0.71
    腔
    -0.71
     weather
    -0.70
    luca
    -0.70
     Funktions
    -0.70
     außergewöhn
    -0.69
    POSITIVE LOGITS
    Hot
    1.34
     Hot
    1.24
     hotter
    1.13
    hot
    1.12
     hottest
    1.02
    HOT
    0.85
    ﷲ
    0.83
     hot
    0.82
    ॉट
    0.81
    冷
    0.81
    Activations Density 0.027%

    No Known Activations