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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 48911
    Prev
    Next
    INDEX
    Explanations

    LaTeX document structure

    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
    🔙
    0.43
     protease
    0.41
    penas
    0.40
     Embora
    0.40
     사람은
    0.40
     NÃO
    0.39
    ścić
    0.39
     APRIL
    0.38
     사람이
    0.38
     Bukan
    0.38
    POSITIVE LOGITS
    uelle
    0.41
     базе
    0.40
    ések
    0.39
    iklet
    0.37
    Recursive
    0.36
    誑
    0.36
    符合
    0.36
    กล่าว
    0.36
    筺
    0.35
    ва
    0.35
    Activations Density 0.007%

    No Known Activations