© 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. 17770
    Prev
    Next
    INDEX
    Explanations

    components in different 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_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
    🫣
    0.43
    டித்து
    0.40
     duvar
    0.39
    🫢
    0.38
     definitivamente
    0.37
    ellido
    0.37
    벽
    0.37
    地下
    0.36
    Jasper
    0.36
    本セット
    0.36
    POSITIVE LOGITS
     components
    0.45
     componente
    0.42
     secret
    0.41
     по
    0.39
     componentes
    0.39
     Î
    0.39
     组件
    0.38
     компонен
    0.37
     Auer
    0.37
     компонентов
    0.37
    Activations Density 0.000%

    No Known Activations