© 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-262K
    7. 123143
    Prev
    Next
    INDEX
    Explanations

    research summarizing provided resource

    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_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
     กราบ
    0.54
     compounding
    0.52
     ব্যান্ড
    0.52
     Бі
    0.49
    ності
    0.48
     বাংলাদেশ
    0.48
    .}}
    0.47
     মৃত্য
    0.47
     ወይም
    0.47
     स्पोर्ट्स
    0.47
    POSITIVE LOGITS
    otype
    0.48
    AS
    0.47
    filed
    0.45
    oss
    0.44
    Q
    0.43
    ba
    0.43
    j
    0.43
    i
    0.42
    ASF
    0.42
    it
    0.42
    Activations Density 0.001%

    No Known Activations