© 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. 78890
    Prev
    Next
    INDEX
    Explanations

    below, then list or examples

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

    below is

    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
    Diabetes
    0.46
     महत्त्वा
    0.46
     मधुमेह
    0.45
    因为它
    0.45
    </h2>
    0.44
    無需
    0.43
    它可以
    0.42
     കഴ
    0.41
    তুমি
    0.41
    हमारे
    0.41
    POSITIVE LOGITS
     are
    0.57
     são
    0.53
    7
    0.51
    3
    0.50
     ي
    0.50
     sont
    0.49
     هنا
    0.49
     befinden
    0.49
     يوجد
    0.49
     hear
    0.48
    Activations Density 0.011%

    No Known Activations