© 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. 5974
    Prev
    Next
    INDEX
    Explanations

    technical terms and various languages

    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
    致力于
    0.38
    实现了
    0.37
     సాధ
    0.36
     specialise
    0.33
    🐻
    0.32
    ามารถ
    0.32
     catapult
    0.31
    腌
    0.31
    uchar
    0.31
    ার্জ
    0.31
    POSITIVE LOGITS
     quaisquer
    0.45
    ча
    0.41
    время
    0.40
    ние
    0.37
    ਿਸ
    0.37
    ka
    0.37
    ktu
    0.36
     yoki
    0.36
    Akt
    0.36
    week
    0.36
    Activations Density 0.110%

    No Known Activations