© 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. 80609
    Prev
    Next
    INDEX
    Explanations

    again entryway

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

    multilingual text and concepts

    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
     the
    0.38
     و
    0.38
     la
    0.37
     dan
    0.35
     quatro
    0.35
     builds
    0.35
     a
    0.35
     D
    0.34
     and
    0.34
     yang
    0.34
    POSITIVE LOGITS
    opcao
    0.36
    ти
    0.36
    iería
    0.35
    ко
    0.35
    бер
    0.35
    אל
    0.35
    ОР
    0.35
    𝗻
    0.34
    нет
    0.33
    бле
    0.33
    Activations Density 0.065%

    No Known Activations