© 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. 224632
    Prev
    Next
    INDEX
    Explanations

    .

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

    biggest misunderstanding

    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
    ılı
    0.42
    并且
    0.42
    🔇
    0.41
    이자
    0.40
    💳
    0.40
    ✚
    0.39
     yarış
    0.39
    还有
    0.39
    🌿
    0.39
    👱
    0.39
    POSITIVE LOGITS
    cU
    0.45
    न्देल
    0.44
    έ
    0.42
     morphisms
    0.41
     grosseur
    0.41
    Databaze
    0.41
    ne
    0.40
    WallArray
    0.40
    ਨੇ
    0.39
     expts
    0.39
    Activations Density 0.027%

    No Known Activations