© 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
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 133016
    Prev
    Next
    INDEX
    Explanations

    Subaru Legacy / Re:Zero

    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
    Champ
    0.46
     z
    0.44
     expense
    0.43
    Expense
    0.42
    MEGA
    0.40
    nts
    0.39
    NQ
    0.38
    Tat
    0.38
    ᴸ
    0.38
    ORDON
    0.38
    POSITIVE LOGITS
     Subaru
    1.07
     Outback
    0.60
     Forester
    0.57
    昴
    0.52
     शिमला
    0.50
     Fuji
    0.50
     Anambra
    0.49
     Fuj
    0.48
     sublimation
    0.48
     Im
    0.48
    Activations Density 0.008%

    No Known Activations