© 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. 84200
    Prev
    Next
    INDEX
    Explanations

    waterframework directive

    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
     Quantitative
    0.38
     ques
    0.38
     Queens
    0.37
     baby
    0.36
    ̈́
    0.36
     »,
    0.36
    </em>
    0.35
     City
    0.35
    ［
    0.35
     deceased
    0.35
    POSITIVE LOGITS
    瀟
    0.43
    жета
    0.41
    nPortIndex
    0.39
    ୌ
    0.39
    сок
    0.39
    اليد
    0.38
    SalesRep
    0.38
     Civ
    0.38
    铬
    0.38
    鉻
    0.38
    Activations Density 0.004%

    No Known Activations