© 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. 131805
    Prev
    Next
    INDEX
    Explanations

    places and transitions

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

    online channels, iterative process, strengthening the

    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
    ਿਲ
    0.37
    均为
    0.37
    :[
    0.37
    cemos
    0.37
    рак
    0.36
     tamper
    0.36
    ੱ
    0.36
    ден
    0.36
    anque
    0.36
    лько
    0.35
    POSITIVE LOGITS
     दूसरों
    0.57
     অন্যরা
    0.52
     Và
    0.48
     :-)
    0.47
     然后
    0.47
    我会
    0.47
     سپس
    0.47
     නමුත්
    0.46
     Então
    0.46
     അല്ലെങ്കിൽ
    0.46
    Activations Density 0.001%

    No Known Activations