© 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-65K
    7. 36121
    Prev
    Next
    INDEX
    Explanations

    Here's a breakdown

    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
     পাচ্ছে
    0.38
    が大
    0.38
    
    0.37
    ──
    0.37
    These
    0.36
    ＝
    0.36
    的には
    0.36
    geräte
    0.36
    vehicle
    0.35
    ﮔ
    0.35
    POSITIVE LOGITS
    собенности
    0.49
     pruebas
    0.44
    •
    0.39
     facts
    0.38
    izquierda
    0.38
     Purnama
    0.38
     peculiarities
    0.38
     •
    0.37
     atentos
    0.37
     stipulations
    0.36
    Activations Density 0.311%

    No Known Activations