© 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. 40-GEMMASCOPE-2-RES-262K
    7. 32399
    Prev
    Next
    INDEX
    Explanations

    AI chatbot disclaimer

    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
     darwin
    0.39
     Alumin
    0.38
     Técn
    0.38
    ancellor
    0.36
     alumin
    0.36
    牪
    0.36
     riten
    0.35
     Бүгенге
    0.35
    uminum
    0.35
     Ayu
    0.35
    POSITIVE LOGITS
    જ
    0.41
    ្នាក់
    0.40
    यं
    0.39
     évidemment
    0.39
    Gust
    0.38
    Hold
    0.38
    BREAK
    0.38
    anone
    0.38
    やや
    0.38
    Cra
    0.38
    Activations Density 0.001%

    No Known Activations