© 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. 111615
    Prev
    Next
    INDEX
    Explanations

    asking about

    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
     कृषि
    0.47
    kinder
    0.45
    န
    0.45
    academy
    0.44
    拡張
    0.43
    omicide
    0.42
     एग्रीकल्चर
    0.42
    ¹.
    0.42
    anwhile
    0.41
     levelled
    0.41
    POSITIVE LOGITS
     cít
    0.48
     respal
    0.47
     vínculos
    0.47
    ನ್‌
    0.47
     obsess
    0.45
     discut
    0.44
     fós
    0.43
     corrigir
    0.43
    SCUS
    0.42
     corrige
    0.41
    Activations Density 0.008%

    No Known Activations