© 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. 10-GEMMASCOPE-RES-131K
    7. 15176
    Prev
    Next
    INDEX
    Explanations

    detecting "hot" followed by a word

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    u
    -1.79
    Ｔ
    -1.60
    )
    -1.55
    “
    -1.53
    A
    -1.50
    Ａ
    -1.48
    (
    -1.45
     began
    -1.45
    Ｆ
    -1.43
     “
    -1.42
    POSITIVE LOGITS
    hot
    1.77
     hot
    1.73
    HOT
    1.71
    Hot
    1.65
    会儿
    1.63
    zości
    1.63
    ции
    1.63
    甍
    1.62
     Luckily
    1.59
    ctivité
    1.57
    Activations Density 0.024%

    No Known Activations