© 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. 22-GEMMASCOPE-2-RES-16K
    7. 2083
    Prev
    Next
    INDEX
    Explanations

    East Asia and West Africa

    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_22_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
    ૫
    0.85
    र
    0.84
    無
    0.83
    Ÿ
    0.82
    Printing
    0.82
     Needless
    0.81
    ਮ
    0.78
    ̀n
    0.76
    ૦
    0.75
    بت
    0.74
    POSITIVE LOGITS
    ensibly
    1.36
    莞
    1.07
    reicher
    1.04
    ERN
    1.02
    ward
    1.01
     그러니까
    0.99
    side
    0.98
     Coast
    0.98
    coast
    0.98
     Timor
    0.97
    Activations Density 0.063%

    No Known Activations