© 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. 13983
    Prev
    Next
    INDEX
    Explanations

    Silas's possessions

    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
    ので
    1.62
    もちろん
    1.05
     불구하고
    1.04
     milliers
    1.02
     след
    1.01
     tas
    0.93
     schm
    0.93
    च
    0.90
    ऱ्या
    0.89
     τα
    0.88
    POSITIVE LOGITS
    s
    3.55
    ের
    2.44
    ों
    2.08
    ים
    2.02
    ات
    1.99
    ség
    1.80
    ्स
    1.79
    ы
    1.58
    sman
    1.56
    ς
    1.55
    Activations Density 0.061%

    No Known Activations