© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 55799
    Prev
    Next
    INDEX
    Explanations

    signs and labels

    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
     trick
    0.43
     ports
    0.41
     imit
    0.40
    孫
    0.40
     tricks
    0.40
    来る
    0.40
     eru
    0.39
    trick
    0.39
    餵
    0.39
     sockets
    0.39
    POSITIVE LOGITS
     plaque
    0.52
     billboard
    0.46
    Opportunity
    0.44
     engraved
    0.43
     पोस्टर
    0.43
     placard
    0.43
    刻
    0.43
     banner
    0.43
    Banner
    0.42
     PLASMA
    0.42
    Activations Density 0.058%

    No Known Activations