© 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. 40-GEMMASCOPE-2-RES-262K
    4. 31861
    Prev
    Next
    INDEX
    Explanations

    Python code and hardware modules

    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
    Distributed
    0.45
     Distributed
    0.41
     형
    0.39
     Wolfe
    0.39
    Amazon
    0.38
    DVD
    0.38
    Schwarz
    0.38
    ยายน
    0.38
    Software
    0.38
     歩
    0.38
    POSITIVE LOGITS
     CIRCUIT
    0.48
     isla
    0.48
     fruta
    0.43
     pulau
    0.43
    readline
    0.42
    ्रल
    0.42
     microSD
    0.42
     Micro
    0.42
     MICRO
    0.42
     uart
    0.42
    Activations Density 0.009%

    No Known Activations