© 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. 31-GEMMASCOPE-2-RES-262K
    7. 25831
    Prev
    Next
    INDEX
    Explanations

    numbers followed by units or context

    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
     T
    0.42
     t
    0.41
     relay
    0.39
     temporary
    0.38
     transient
    0.38
    стой
    0.38
     briefly
    0.37
     Briefly
    0.37
    inne
    0.36
     Sim
    0.36
    POSITIVE LOGITS
    성과
    0.47
    성
    0.44
    뷔
    0.43
     conflit
    0.41
    만
    0.40
     відкри
    0.39
     경험
    0.39
    公开
    0.39
     cohomology
    0.39
     pengalaman
    0.39
    Activations Density 0.000%

    No Known Activations