© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 83444
    Prev
    Next
    INDEX
    Explanations

    bridge, trips, agents, man

    np_acts-logits-general · gemini-2.5-flash-lite

    introducing explanatory clauses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    できない
    0.60
    اید
    0.54
     productColor
    0.51
    यहां
    0.50
    えない
    0.49
     Вайлд
    0.48
    োলজি
    0.48
    ₎
    0.48
    মানে
    0.48
    媲
    0.47
    POSITIVE LOGITS
     pons
    0.48
     concerted
    0.46
     shows
    0.45
     significant
    0.45
     reis
    0.45
     trips
    0.44
     pont
    0.44
     bors
    0.44
     elt
    0.44
     nep
    0.44
    Activations Density 0.001%

    No Known Activations