© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 11813
    Prev
    Next
    INDEX
    Explanations

    requests to explain

    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
    elines
    2.88
    ا
    2.66
    jPanel
    2.51
    м
    2.37
     обсужда
    2.32
    𝐃
    2.32
    ing
    2.25
    userData
    2.25
    zmdi
    2.23
     helst
    2.23
    POSITIVE LOGITS
    𝗮
    2.99
    𝗶
    2.87
    𝗲
    2.79
    ات
    2.76
    𝗹
    2.55
    𝗻
    2.34
    ن
    2.12
    𝗔
    2.08
    𝗱
    2.07
    𝘆
    2.07
    Activations Density 0.115%

    No Known Activations