© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 876
    Prev
    Next
    INDEX
    Explanations

    foreign language words

    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_16k_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
    П
    0.55
    Í
    0.52
    Color
    0.52
    。
    0.51
    Х
    0.50
    Й
    0.50
    Č
    0.49
    Ó
    0.48
    Ви
    0.48
    Coming
    0.48
    POSITIVE LOGITS
     conseiller
    0.48
     beziehen
    0.48
     baju
    0.47
     હાઉસ
    0.47
     sujet
    0.45
     уйнау
    0.45
    സിന്റെ
    0.44
     chamar
    0.44
     wodurch
    0.43
     bezieht
    0.43
    Activations Density 0.000%

    No Known Activations