© 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. 34906
    Prev
    Next
    INDEX
    Explanations

    oceans, marina, printing, screen, circulation

    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
     کام
    0.40
    セラ
    0.40
    тента
    0.39
    ┳
    0.39
    кинуло
    0.38
    SUMMARY
    0.38
    mobility
    0.38
     moan
    0.37
    ယာ
    0.37
     exasper
    0.37
    POSITIVE LOGITS
     et
    0.59
     are
    0.52
     والتي
    0.51
     may
    0.49
     ฉ
    0.48
    eds
    0.47
     should
    0.46
     habite
    0.46
     grupa
    0.46
     uma
    0.46
    Activations Density 0.000%

    No Known Activations