© 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. 224968
    Prev
    Next
    INDEX
    Explanations

    describing specific details or occurrences

    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
     Stat
    0.39
    䢎
    0.38
    ennies
    0.37
    elte
    0.36
     réun
    0.36
     Nix
    0.36
    ধীন
    0.36
     conduite
    0.36
     ännu
    0.36
     naud
    0.35
    POSITIVE LOGITS
    пень
    0.41
     practicality
    0.39
    óra
    0.38
    practical
    0.37
    
    0.37
     preventative
    0.36
    󰡕
    0.36
    mole
    0.36
    スプレイ
    0.36
    Instantiation
    0.35
    Activations Density 0.000%

    No Known Activations