© 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. 31-GEMMASCOPE-2-RES-65K
    7. 49818
    Prev
    Next
    INDEX
    Explanations

    often made or called

    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_31_width_65k_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
     insufficient
    0.46
     וי
    0.43
     ウィ
    0.43
     अनुभूति
    0.43
    ao
    0.42
    u
    0.42
     restricts
    0.42
     probleme
    0.41
     যুগের
    0.41
     A
    0.40
    POSITIVE LOGITS
    埝
    0.48
    رة
    0.45
    র্ড
    0.43
    REACTOR
    0.42
    رد
    0.42
    회사
    0.40
     similaire
    0.39
    执行
    0.38
    सिस
    0.38
     जेटली
    0.38
    Activations Density 0.002%

    No Known Activations