© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 28040
    Prev
    Next
    INDEX
    Explanations

    murder, people-pleasing, chargers

    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_65k_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
    ት
    0.44
    Laura
    0.43
     iguales
    0.41
    منى
    0.40
    ucidation
    0.39
    偻
    0.39
    лях
    0.39
     człowieka
    0.38
    rocytes
    0.38
    ایید
    0.38
    POSITIVE LOGITS
    <0x0E>
    0.45
     mehrerer
    0.45
     Sekolah
    0.44
     особенно
    0.42
    等方面
    0.42
     போன்றவற்ற
    0.41
     داشت
    0.40
    峇
    0.40
    などで
    0.40
     Особенно
    0.40
    Activations Density 0.027%

    No Known Activations