© 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-262K
    7. 36121
    Prev
    Next
    INDEX
    Explanations

    foreign capital

    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
     сильнее
    0.51
    뮐
    0.45
    FREQUENCY
    0.45
    权的
    0.44
     deň
    0.44
     اختی
    0.43
    𝐚
    0.43
    сії
    0.42
     विश्वसनीयता
    0.42
    闩
    0.42
    POSITIVE LOGITS
    program
    0.48
     foreign
    0.47
     program
    0.46
     Foreign
    0.46
     proposal
    0.45
     Carnegie
    0.45
    transform
    0.45
     TED
    0.43
    foreign
    0.43
    Foreign
    0.42
    Activations Density 0.002%

    No Known Activations