© 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. 12984
    Prev
    Next
    INDEX
    Explanations

    top_p parameter

    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
    و
    0.84
     нен
    0.81
    ต้อง
    0.78
    снаб
    0.76
    or
    0.76
     meng
    0.74
    𝐎
    0.72
    മായ
    0.71
     pav
    0.71
     કરવું
    0.71
    POSITIVE LOGITS
    অত
    1.11
    rigues
    1.08
    hin
    1.06
     chiqar
    0.99
    hwa
    0.97
     fortsatt
    0.96
    his
    0.95
    வாகும்
    0.94
    ശ
    0.94
    chodzi
    0.93
    Activations Density 0.004%

    No Known Activations