© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 28961
    Prev
    Next
    INDEX
    Explanations

    prediction and future likelihood

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_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
    狍
    0.51
     våra
    0.50
     sowohl
    0.50
     számos
    0.50
     والتي
    0.50
    翮
    0.50
     mengembangkan
    0.49
    䢀
    0.49
     하는
    0.49
    ığımız
    0.49
    POSITIVE LOGITS
     repente
    0.51
     hehe
    0.48
    laughs
    0.46
    haha
    0.45
     :)
    0.45
    becue
    0.45
    。
    0.45
     it
    0.44
     ！
    0.44
    ql
    0.43
    Activations Density 0.013%

    No Known Activations