© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 52570
    Prev
    Next
    INDEX
    Explanations

    describes or defines characteristics

    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
     любовь
    0.50
     हळ
    0.49
     Однако
    0.48
     keing
    0.47
    substrate
    0.47
    受け
    0.46
    䀖
    0.46
    侕
    0.45
     इज़
    0.45
     Benim
    0.45
    POSITIVE LOGITS
    ’
    0.47
     solver
    0.44
     compressed
    0.44
    is
    0.43
     commenter
    0.42
    онів
    0.42
     diventa
    0.41
     advanced
    0.41
     cube
    0.40
    du
    0.40
    Activations Density 0.003%

    No Known Activations