© 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. 5988
    Prev
    Next
    INDEX
    Explanations

    web and software development terms

    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
     oldukça
    1.59
    께
    1.56
     perdu
    1.54
     dolayı
    1.45
    𝘁
    1.40
     kandungan
    1.39
    ධ
    1.38
    ｭ
    1.38
    ਢ
    1.36
    𝘄
    1.33
    POSITIVE LOGITS
    ′
    1.75
    儡
    1.54
    heon
    1.51
    푚
    1.48
    dpi
    1.44
    chromosome
    1.43
     ′
    1.37
    ivated
    1.37
    dangerous
    1.37
    pace
    1.35
    Activations Density 0.032%

    No Known Activations