© 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-65K
    7. 48176
    Prev
    Next
    INDEX
    Explanations

    magical storms or friendly collaboration

    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_65k_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
    लेखित
    0.43
    ບໍ່
    0.41
     éd
    0.41
    informative
    0.41
     safeguard
    0.41
    Р
    0.41
     systém
    0.41
    은
    0.41
    忥
    0.40
    contract
    0.39
    POSITIVE LOGITS
     Parad
    0.40
     cerdo
    0.40
     Baroque
    0.39
     boring
    0.38
     Renaissance
    0.38
     samband
    0.38
     jugando
    0.38
     SCE
    0.37
    ടൊപ്പം
    0.37
     boredom
    0.37
    Activations Density 0.025%

    No Known Activations