© 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. 63505
    Prev
    Next
    INDEX
    Explanations

    hot or warm food

    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_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
     Gayle
    -0.73
    idalgo
    -0.71
    ่วย
    -0.71
     Pollut
    -0.70
    掃除
    -0.69
     nguồn
    -0.68
    UNA
    -0.68
    Washing
    -0.65
     JY
    -0.64
    YH
    -0.64
    POSITIVE LOGITS
     hot
    5.28
    hot
    4.09
    Hot
    3.83
     Hot
    3.63
    HOT
    3.36
     HOT
    3.31
     горя
    3.31
     warm
    3.25
    热
    2.86
     sıcak
    2.77
    Activations Density 0.050%

    No Known Activations