© 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. 46530
    Prev
    Next
    INDEX
    Explanations

    types of questions

    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
    commodity
    0.45
     teórico
    0.44
    ␣
    0.43
    呑
    0.43
    ásticas
    0.43
    劈
    0.42
    ꞌ
    0.42
    optim
    0.41
    criterion
    0.41
     konto
    0.41
    POSITIVE LOGITS
    ש
    0.61
    шая
    0.49
    ش
    0.49
    자
    0.48
    ব
    0.46
     reprint
    0.46
     overlapped
    0.45
    我们也
    0.45
     behaviors
    0.44
    ж
    0.44
    Activations Density 0.020%

    No Known Activations