© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 45172
    Prev
    Next
    INDEX
    Explanations

    stretching

    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
     እንቅስቃሴ
    0.49
     $('#
    0.48
     laptop
    0.45
    墊
    0.45
     vectors
    0.45
     usability
    0.45
     studio
    0.44
     iPads
    0.44
     activities
    0.43
     purchases
    0.43
    POSITIVE LOGITS
    겸
    0.39
    Lincoln
    0.39
     የሚያ
    0.38
    chluss
    0.37
    淋
    0.37
    羊
    0.36
    DBES
    0.36
     отличаются
    0.36
    弄
    0.36
     غز
    0.36
    Activations Density 0.029%

    No Known Activations