© 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. 17-GEMMASCOPE-2-RES-16K
    7. 13883
    Prev
    Next
    INDEX
    Explanations

    "was an error" or "was a problem"

    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_17_width_16k_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
    ed
    0.92
    t
    0.87
    ت
    0.84
     ВО
    0.80
    تس
    0.79
     алуу
    0.78
    h
    0.77
    ร์
    0.75
    т
    0.75
    Bond
    0.74
    POSITIVE LOGITS
     Neither
    1.01
     às
    0.99
     crítica
    0.95
     intentar
    0.95
     Ihre
    0.94
     ils
    0.93
     enviados
    0.91
    Idents
    0.90
     доста
    0.88
     neither
    0.88
    Activations Density 0.005%

    No Known Activations