© 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-16K
    7. 3734
    Prev
    Next
    INDEX
    Explanations

    but not

    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_16k_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
    Những
    0.41
     முற்றிலும்
    0.41
    {\
    0.40
    írus
    0.40
     durchaus
    0.38
     coinciding
    0.38
    ​—
    0.38
    ícios
    0.38
    featuring
    0.37
     ដោយ
    0.37
    POSITIVE LOGITS
    而不是
    0.52
    而非
    0.48
    则
    0.45
    ร์
    0.43
     জানতে
    0.43
    ではなく
    0.42
    但不
    0.42
     preprocess
    0.41
     SURVEY
    0.40
     کرن
    0.40
    Activations Density 0.223%

    No Known Activations