© 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. 29322
    Prev
    Next
    INDEX
    Explanations

    what's up?

    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
    Send
    0.45
    Events
    0.44
    Don
    0.43
    定义
    0.43
     defend
    0.43
     للم
    0.43
    Martin
    0.42
    对
    0.42
    비
    0.42
     في
    0.41
    POSITIVE LOGITS
     amounting
    0.51
     temporal
    0.47
     alloying
    0.45
     fringes
    0.44
     drowsiness
    0.44
     alken
    0.43
     moieties
    0.43
     downregulation
    0.42
     peculiar
    0.42
     leafy
    0.42
    Activations Density 0.003%

    No Known Activations