© 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. 9-GEMMASCOPE-2-RES-16K
    7. 2574
    Prev
    Next
    INDEX
    Explanations

    sparkling and sweet things

    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_9_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
    й
    3.37
    ка
    2.77
    ্য
    2.73
    ك
    2.58
    ik
    2.58
    мо
    2.53
    ి
    2.49
    ि
    2.36
    ishly
    2.34
    list
    2.31
    POSITIVE LOGITS
    ć
    2.65
    yzed
    2.52
    घाट
    2.48
     coincided
    2.47
    یس
    2.41
     inflow
    2.40
    eus
    2.39
     কপ
    2.39
    eol
    2.35
    gifs
    2.33
    Activations Density 0.198%

    No Known Activations