© 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. 6407
    Prev
    Next
    INDEX
    Explanations

    bullet points

    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
     firstly
    0.45
     ①
    0.42
     schematically
    0.41
    一是
    0.41
     solutes
    0.38
     Firstly
    0.36
     smoothed
    0.35
     faceted
    0.35
    ①
    0.35
     flancs
    0.34
    POSITIVE LOGITS
    *
    0.57
    
    0.36
    â
    0.34
    ún
    0.34
    +
    0.34
    ?
    0.34
    î
    0.34
     Throughout
    0.32
    这些
    0.32
    atto
    0.32
    Activations Density 0.040%

    No Known Activations