© 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. 16-GEMMASCOPE-2-RES-262K
    7. 120552
    Prev
    Next
    INDEX
    Explanations

    Law and its commandments

    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_16_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
     Executor
    0.55
     क्रिया
    0.51
     çıkt
    0.50
     iht
    0.50
     executar
    0.50
     Estr
    0.50
     EditText
    0.49
    芡
    0.49
     are
    0.48
     igu
    0.48
    POSITIVE LOGITS
    MASK
    0.51
    aligned
    0.50
    DEL
    0.50
    p
    0.49
    MATCH
    0.49
    bell
    0.49
    PIPE
    0.48
    Бу
    0.47
    CLUDES
    0.47
    inline
    0.46
    Activations Density 0.001%

    No Known Activations