© 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-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 2642
    Prev
    Next
    INDEX
    Explanations

    skin tones, hair types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_width_16k_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
     hear
    0.76
    渣
    0.67
     hearing
    0.65
     hears
    0.65
    ጠ
    0.65
    hearing
    0.63
    hairstyle
    0.62
    heard
    0.62
    olari
    0.62
    म्म
    0.62
    POSITIVE LOGITS
     follicles
    0.68
     care
    0.68
     Care
    0.67
     conductance
    0.66
     follicle
    0.64
     flanking
    0.60
     அப்ப
    0.59
    帼
    0.59
     dens
    0.58
     clinics
    0.57
    Activations Density 0.118%

    No Known Activations