© 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. 46386
    Prev
    Next
    INDEX
    Explanations

    preposition, instead, fall, paying

    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
     myn
    0.45
    리면
    0.40
    මාන්
    0.39
     στε
    0.38
     daarbij
    0.37
    旂
    0.37
    单元
    0.36
    utherford
    0.36
    发生在
    0.36
    空间
    0.35
    POSITIVE LOGITS
     Terbaru
    0.43
     Mermaid
    0.43
    这篇文章
    0.42
     कौशिक
    0.42
     questo
    0.41
     Diese
    0.41
     Ejemplo
    0.41
    ल
    0.40
    archivo
    0.40
     Kauai
    0.40
    Activations Density 0.006%

    No Known Activations