© 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. 4951
    Prev
    Next
    INDEX
    Explanations

    resembling a

    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
     dénom
    0.41
     indicative
    0.40
     đủ
    0.39
     called
    0.39
     peripheral
    0.38
     peripher
    0.38
     sogenannten
    0.37
    힝
    0.37
     reachable
    0.37
     obstructing
    0.36
    POSITIVE LOGITS
     будто
    0.52
     마치
    0.52
    まるで
    0.52
     एखाद्या
    0.51
    火山
    0.51
     অনেকটা
    0.49
    普通
    0.48
     एखा
    0.48
    战场
    0.45
    埃及
    0.45
    Activations Density 0.339%

    No Known Activations