© 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. 10780
    Prev
    Next
    INDEX
    Explanations

    multilingual connectors and punctuation

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

    shapes responsive behavior

    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
    /
    0.58
    ↵
    0.57
    ’
    0.50
    *
    0.47
     *
    0.47
     veya
    0.47
    Ин
    0.47
     चाहिँ
    0.46
     või
    0.46
     jeśli
    0.46
    POSITIVE LOGITS
    했고
    0.71
    并通过
    0.55
     અને
    0.54
    ၊
    0.52
    ،
    0.51
     এবং
    0.51
     astonished
    0.50
    はなく
    0.49
    었고
    0.49
     และ
    0.48
    Activations Density 0.001%

    No Known Activations