© 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. 53-GEMMASCOPE-2-RES-262K
    7. 166948
    Prev
    Next
    INDEX
    Explanations

    outside the box

    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_53_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
    ampil
    0.43
     vlá
    0.41
    ">)</
    0.38
    刻
    0.38
    hæng
    0.37
     wrapped
    0.37
    rimidin
    0.37
    婦
    0.37
     розта
    0.36
     च्या
    0.36
    POSITIVE LOGITS
     heaven
    0.58
     Heaven
    0.55
     bench
    0.52
     deep
    0.48
     دليل
    0.48
     benches
    0.48
     television
    0.46
     completion
    0.44
     eviction
    0.44
     Completion
    0.42
    Activations Density 0.004%

    No Known Activations