© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 21770
    Prev
    Next
    INDEX
    Explanations

    critical noun phrases

    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
    මය
    0.42
     cruc
    0.41
    శ్వ
    0.41
     প্রতীক
    0.40
     originalmente
    0.40
    闊
    0.40
    形態
    0.40
     acknowled
    0.39
     điều
    0.39
    𝙏
    0.38
    POSITIVE LOGITS
     Critical
    1.01
    Critical
    0.99
    critical
    0.95
     critical
    0.94
     крити
    0.90
     kritis
    0.87
     criticality
    0.82
     krit
    0.79
     critically
    0.72
     Crit
    0.71
    Activations Density 0.004%

    No Known Activations