© 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. 40-GEMMASCOPE-2-RES-262K
    7. 17515
    Prev
    Next
    INDEX
    Explanations

    Silent, Variable, Fast, Zero

    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
     دقت
    0.40
    ሬ
    0.40
    Après
    0.39
    0.38
    能
    0.37
    、
    0.37
    พ
    0.37
    مة
    0.37
     Après
    0.37
    트
    0.37
    POSITIVE LOGITS
    oth
    0.46
     Archivado
    0.43
    ompok
    0.40
     เนาะ
    0.39
    욱
    0.39
     कार्यकारी
    0.39
    rekli
    0.38
     Consultado
    0.38
    फारिश
    0.37
    opo
    0.37
    Activations Density 0.000%

    No Known Activations