© 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. 36398
    Prev
    Next
    INDEX
    Explanations

    Romania, Romanian,

    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
    ём
    0.56
    слі
    0.56
     باسکٹ
    0.56
     функції
    0.53
     вікі
    0.52
    ),]$
    0.52
     пі
    0.51
    لین
    0.50
    켓
    0.49
    Maui
    0.48
    POSITIVE LOGITS
     Romanian
    1.88
     Romania
    1.67
     Bucharest
    1.55
     România
    1.30
     Bucure
    1.30
    Romania
    1.30
     Cluj
    1.30
     Moldova
    1.08
     Ruman
    1.07
     Bulgaria
    1.05
    Activations Density 0.031%

    No Known Activations