© 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. 1752
    Prev
    Next
    INDEX
    Explanations

    units followed by context

    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
     деся
    0.75
     months
    0.74
    십
    0.74
     billions
    0.71
    S
    0.70
    큘
    0.68
     million
    0.68
     hours
    0.68
     weeks
    0.68
     годы
    0.67
    POSITIVE LOGITS
    짜
    1.49
    씩
    1.15
    বিশিষ্ট
    1.05
    以内
    0.92
    以上的
    0.90
    ²+
    0.90
     olds
    0.87
    ずつ
    0.87
     scorers
    0.86
     짜
    0.84
    Activations Density 0.488%

    No Known Activations