© 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-65K
    7. 5137
    Prev
    Next
    INDEX
    Explanations

    single codebase

    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
    就
    0.50
     estimate
    0.49
     heure
    0.49
    מוד
    0.49
    ↵
    0.48
    ل
    0.46
     adept
    0.46
    你
    0.45
     potion
    0.45
    ཇ
    0.44
    POSITIVE LOGITS
    taire
    0.47
    ные
    0.46
    enarios
    0.45
    쟁
    0.45
    deki
    0.44
    toBeTruthy
    0.43
    麾
    0.42
    enger
    0.42
     அணி
    0.42
    了嗎
    0.42
    Activations Density 0.000%

    No Known Activations