© 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. 110883
    Prev
    Next
    INDEX
    Explanations

    your story

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

    most trusted format

    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
     ;;
    0.51
     antider
    0.50
     ★★
    0.50
     നടപ
    0.49
     データ
    0.49
     場所
    0.49
     コンパクト
    0.49
     ケース
    0.48
     นับ
    0.47
     вычисли
    0.47
    POSITIVE LOGITS
    ب
    0.52
     lw
    0.52
    f
    0.49
     compensate
    0.49
    wiz
    0.47
    up
    0.47
     squadra
    0.45
    ia
    0.45
    irr
    0.45
    merge
    0.44
    Activations Density 0.000%

    No Known Activations