© 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. 17584
    Prev
    Next
    INDEX
    Explanations

    preposition 'на' + context

    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
     ssize
    0.50
    germeister
    0.44
     যু
    0.41
    ..............
    0.41
     按
    0.41
    налу
    0.40
     zaradi
    0.40
    (__
    0.40
    按
    0.39
     ग्वालियर
    0.38
    POSITIVE LOGITS
     протяжении
    0.68
     behalf
    0.65
     участке
    0.63
     рынке
    0.63
     примере
    0.63
     وعلى
    0.63
     terenie
    0.61
     території
    0.61
     základě
    0.61
     этапе
    0.60
    Activations Density 0.004%

    No Known Activations