© 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. 111724
    Prev
    Next
    INDEX
    Explanations

    complicated subjects or tasks

    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
     ي
    0.52
    Ε
    0.48
     Е
    0.46
    ческий
    0.46
    Н
    0.44
     в
    0.44
     По
    0.43
     ת
    0.43
     Editar
    0.43
    探讨
    0.43
    POSITIVE LOGITS
    水中
    0.44
    cooking
    0.42
    lier
    0.41
    水量
    0.41
    gers
    0.40
    ut
    0.39
    rived
    0.39
    resses
    0.39
    stopper
    0.39
     zucchero
    0.38
    Activations Density 0.008%

    No Known Activations