© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 6156
    Prev
    Next
    INDEX
    Explanations

    hu and hum

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

    Hugging Face

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    handed
    0.41
    捗
    0.40
     Declar
    0.36
     फं
    0.36
     Oph
    0.36
     homomorphism
    0.36
    is
    0.36
    halogen
    0.36
    廠
    0.35
    hele
    0.35
    POSITIVE LOGITS
     HU
    0.70
     胡
    0.66
     ху
    0.65
    qvarna
    0.64
     হু
    0.61
     hu
    0.59
     Ху
    0.57
    Hu
    0.54
    Hum
    0.54
     HUM
    0.52
    Activations Density 0.043%

    No Known Activations