© 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. 179522
    Prev
    Next
    INDEX
    Explanations

    systems and services

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

    sometimes to

    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
     ήταν
    0.54
     निकालने
    0.52
     expresión
    0.49
    тони
    0.49
     diputado
    0.48
     articulation
    0.48
     ά
    0.48
     سازی
    0.48
    ത്തിയാ
    0.48
     analisar
    0.48
    POSITIVE LOGITS
     gemäß
    0.48
    mesh
    0.45
    $(".
    0.43
    mode
    0.43
    buttons
    0.43
    uche
    0.42
    騨
    0.41
    texts
    0.41
    kd
    0.41
    table
    0.41
    Activations Density 0.001%

    No Known Activations