© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 40506
    Prev
    Next
    INDEX
    Explanations

    used as or for

    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
    Data
    0.44
     Überblick
    0.43
     انصاف
    0.42
    Est
    0.42
    Ч
    0.41
     diligent
    0.40
     Onder
    0.40
    Під
    0.40
    ੀ
    0.40
    ٽ
    0.39
    POSITIVE LOGITS
     xấu
    0.47
    かもし
    0.47
     পরে
    0.46
     станет
    0.46
     với
    0.45
    রাষ্ট
    0.45
    㼛
    0.45
     transfected
    0.45
     କରି
    0.45
    <unused360>
    0.44
    Activations Density 0.013%

    No Known Activations