© 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. 52744
    Prev
    Next
    INDEX
    Explanations

    class names after is

    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
    ú
    0.43
    úd
    0.42
    ウ
    0.38
    高兴
    0.37
    उसके
    0.37
    putes
    0.37
    ̪
    0.36
     hạnh
    0.36
     имена
    0.35
    ֤
    0.35
    POSITIVE LOGITS
    িমুখে
    0.44
     wavefunction
    0.41
    руют
    0.40
    رر
    0.40
     Catedral
    0.40
     refreshed
    0.39
     inplace
    0.39
     tasked
    0.39
     laporan
    0.39
     coworker
    0.39
    Activations Density 0.006%

    No Known Activations