© 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. 7757
    Prev
    Next
    INDEX
    Explanations

    Russian prepositions and conjunctions

    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
    льнай
    0.59
    Ꮼ
    0.57
     zuten
    0.57
     cartes
    0.56
     sämt
    0.56
     contrats
    0.56
    혔
    0.56
     crée
    0.55
     laag
    0.55
    핞
    0.55
    POSITIVE LOGITS
     Ко
    0.85
     Для
    0.85
     В
    0.83
     в
    0.80
     Если
    0.79
     По
    0.79
     На
    0.79
     До
    0.79
     С
    0.79
     У
    0.79
    Activations Density 0.008%

    No Known Activations