© 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. 30830
    Prev
    Next
    INDEX
    Explanations

    tokenizing text into specific parts

    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
     U
    0.55
     India
    0.50
    item
    0.50
    wang
    0.48
    ost
    0.47
    np
    0.46
    begin
    0.45
    manage
    0.44
    lo
    0.44
     repayment
    0.44
    POSITIVE LOGITS
    ждении
    0.48
    Ⲁ
    0.48
     ประก
    0.47
     हमे
    0.45
    Ϥ
    0.44
    ﹑
    0.44
    Địa
    0.44
     dwóch
    0.43
    ruari
    0.43
    蜼
    0.43
    Activations Density 0.024%

    No Known Activations