© 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-262K
    7. 201768
    Prev
    Next
    INDEX
    Explanations

    foreign words and phrases

    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_262k_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
     interfered
    0.44
     Salary
    0.41
    新型コロナ
    0.41
     Covid
    0.41
     Oxygen
    0.40
     COVID
    0.40
    }$\
    0.40
     சம்ப
    0.39
     Flipkart
    0.39
     Liability
    0.39
    POSITIVE LOGITS
     stables
    0.48
     tradicion
    0.48
     firmer
    0.46
    stit
    0.46
    റിയ
    0.46
     ediciones
    0.45
     стаби
    0.45
     conno
    0.45
     mainline
    0.44
    𝗲
    0.44
    Activations Density 0.014%

    No Known Activations