© 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. 29-GEMMASCOPE-2-RES-16K
    7. 2359
    Prev
    Next
    INDEX
    Explanations

    example usage:

    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_29_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
    回来了
    0.69
    していますが
    0.68
    はず
    0.67
    してきました
    0.67
     ক্ষুদ্র
    0.65
    使用的
    0.65
    北
    0.63
     그럼
    0.62
    ready
    0.62
    kT
    0.62
    POSITIVE LOGITS
     till
    1.16
     viz
    1.06
     upto
    1.05
    Till
    1.01
     Till
    1.01
     envisaged
    1.00
     apart
    0.98
     duly
    0.96
     mentioning
    0.92
     owing
    0.92
    Activations Density 0.062%

    No Known Activations