© 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-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 1214
    Prev
    Next
    INDEX
    Explanations

    a beautiful

    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
    ℤ
    0.66
     chrono
    0.64
    Proguard
    0.64
    方針
    0.63
     warehouse
    0.62
     detections
    0.62
     reintegr
    0.62
     hardcore
    0.62
    垡
    0.62
     BMX
    0.62
    POSITIVE LOGITS
     beautiful
    4.62
     Beautiful
    4.45
    beautiful
    4.40
    Beautiful
    4.27
     BEAUT
    4.21
     gorgeous
    4.12
     beauty
    4.09
     아름
    3.90
    美しい
    3.83
    beauty
    3.76
    Activations Density 1.309%

    No Known Activations