© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-262K
    7. 147151
    Prev
    Next
    INDEX
    Explanations

    scooters, anaphylaxis, Saint Laurent

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ্যে
    0.67
    ẩ
    0.65
    =|
    0.64
    мени
    0.59
    sts
    0.58
    วย
    0.58
    using
    0.57
     ανθ
    0.56
    アリ
    0.56
     明
    0.55
    POSITIVE LOGITS
     ferment
    0.85
     infraestructura
    0.84
     Foy
    0.84
     Fer
    0.84
    हट
    0.82
     മുസ്‌
    0.81
     observaciones
    0.80
     reducir
    0.79
    Fer
    0.78
     Mü
    0.78
    Activations Density 0.002%

    No Known Activations