© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 161841
    Prev
    Next
    INDEX
    Explanations

    applying Application Layer

    np_acts-logits-general · gemini-2.5-flash-lite

    describing images and pictures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     менедж
    0.49
    크
    0.48
     гео
    0.46
     продукт
    0.46
     بك
    0.45
    감독
    0.45
    櫒
    0.45
     ব্র্যান্ড
    0.45
    Ⴀ
    0.45
     форма
    0.44
    POSITIVE LOGITS
     enclave
    0.58
     sôi
    0.47
     Responsibility
    0.44
     Territories
    0.43
     आतंकी
    0.42
     Terror
    0.42
     Trap
    0.42
     nihil
    0.42
     eighties
    0.42
     Vegetables
    0.41
    Activations Density 0.001%

    No Known Activations