© 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. 184361
    Prev
    Next
    INDEX
    Explanations

    commercial purpose

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

    descriptions of how systems talk

    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
    хід
    0.45
    鏗
    0.44
    λά
    0.44
     retali
    0.44
    व्यवस्था
    0.43
    ພວກເຮ
    0.43
    nw
    0.43
    꼈
    0.43
     території
    0.43
    ার্থক
    0.43
    POSITIVE LOGITS
     medit
    0.44
     maad
    0.44
     আন্দোল
    0.42
     TextEditing
    0.40
     bhikkhu
    0.40
     billiard
    0.39
     hak
    0.39
     memilih
    0.39
     معلم
    0.39
     پرس
    0.39
    Activations Density 0.001%

    No Known Activations