© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 117938
    Prev
    Next
    INDEX
    Explanations

    words related to "spit"

    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
    setFill
    -0.72
     hom
    -0.70
    واء
    -0.70
     Kritik
    -0.68
    pot
    -0.67
    皇
    -0.66
     depletion
    -0.65
     Raza
    -0.65
    pruch
    -0.65
     crustace
    -0.65
    POSITIVE LOGITS
     Spit
    0.83
    stv
    0.77
     vyš
    0.75
    Urine
    0.75
    предели
    0.72
    👲
    0.71
    Spit
    0.71
     Spice
    0.70
    Flick
    0.70
    venom
    0.69
    Activations Density 0.037%

    No Known Activations