© 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-262K
    7. 127117
    Prev
    Next
    INDEX
    Explanations

    Argentine regional

    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
     धो
    0.49
    WERS
    0.49
     CDMA
    0.48
     వల్ల
    0.46
    व
    0.46
     सहयोग
    0.46
    یان
    0.46
     Vn
    0.46
     ਕੁ
    0.46
    вки
    0.45
    POSITIVE LOGITS
     Secular
    0.43
     Number
    0.42
     csoport
    0.41
    世
    0.41
     prone
    0.41
    ode
    0.41
     style
    0.41
     accompan
    0.41
     değer
    0.40
     semplici
    0.39
    Activations Density 0.005%

    No Known Activations