© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 194648
    Prev
    Next
    INDEX
    Explanations

    within

    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_40_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
    मोरी
    0.40
    Ꮑ
    0.40
    奚
    0.39
    ittää
    0.38
     ध्वस्त
    0.37
    atuan
    0.37
     결과를
    0.37
    Ꮦ
    0.37
    沭
    0.36
    生地
    0.36
    POSITIVE LOGITS
     composers
    0.43
     ambitious
    0.41
     frequent
    0.41
     std
    0.39
    发育
    0.38
     fréquente
    0.37
     czę
    0.37
    Frequent
    0.37
     semelhantes
    0.37
     consumption
    0.36
    Activations Density 0.000%

    No Known Activations