© 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. 45546
    Prev
    Next
    INDEX
    Explanations

    words starting with Hum

    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
    ldern
    -0.80
     faith
    -0.78
     Bewer
    -0.76
    場所
    -0.75
     paese
    -0.74
     practica
    -0.74
     realised
    -0.73
     juiz
    -0.73
     heral
    -0.73
     reinforced
    -0.73
    POSITIVE LOGITS
     Hum
    2.14
    Hum
    1.91
     hum
    1.67
    hum
    1.61
     HUM
    1.38
    HUM
    1.26
     Hummel
    1.21
     humming
    1.17
     humb
    1.04
    哼
    1.01
    Activations Density 0.016%

    No Known Activations