© 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-16K
    7. 8010
    Prev
    Next
    INDEX
    Explanations

    how things relate

    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
    大
    0.89
    ح
    0.80
    0
    0.78
     περίπτωση
    0.78
    ０
    0.65
    irá
    0.65
     переда
    0.61
    ăți
    0.61
    手
    0.61
    𝟬
    0.61
    POSITIVE LOGITS
     relationship
    1.06
     Relationship
    0.95
    的关系
    0.93
    关系
    0.86
    IN
    0.84
    relationship
    0.84
    p
    0.82
     RELATION
    0.80
     relation
    0.79
     ilişk
    0.79
    Activations Density 0.142%

    No Known Activations