© 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. 136156
    Prev
    Next
    INDEX
    Explanations

    leave or if

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

    describing attributes or conditions

    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
     Panchayat
    0.44
     lav
    0.43
     perubahan
    0.42
    Turns
    0.41
    綴
    0.41
     Warna
    0.40
    yeh
    0.40
    rach
    0.39
    semanticweb
    0.39
    蛻
    0.39
    POSITIVE LOGITS
     mnie
    0.54
     međ
    0.50
     сына
    0.44
     깔
    0.44
     پیم
    0.44
    ැබ
    0.43
    ენ
    0.43
     espírito
    0.43
     очи
    0.43
     نیست
    0.42
    Activations Density 0.000%

    No Known Activations