© 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. 7231
    Prev
    Next
    INDEX
    Explanations

    connecting

    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
    0
    0.83
    <0x80>
    0.76
    ០
    0.70
    ０
    0.69
    𝟎
    0.66
    يز
    0.64
     وزير
    0.63
    ૦
    0.63
    
    0.61
    ري
    0.61
    POSITIVE LOGITS
     connect
    1.30
     connecting
    1.26
     connects
    1.23
     연결
    1.21
     connection
    1.19
    เชื่อม
    1.14
    连接
    1.13
     Connecting
    1.11
     Connect
    1.09
     menghub
    1.09
    Activations Density 0.238%

    No Known Activations