© 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. 4083
    Prev
    Next
    INDEX
    Explanations

    describes purpose or state

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

    a followed by adjective

    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
    Watched
    0.42
    सुबह
    0.42
     تف
    0.41
    栏
    0.41
     σκ
    0.40
     bracing
    0.40
    박
    0.39
    开始了
    0.39
     efectos
    0.39
     Effects
    0.39
    POSITIVE LOGITS
    يد
    0.58
    краё
    0.52
    يز
    0.50
     Bedi
    0.49
    eil
    0.49
    экономи
    0.48
    ਾ
    0.48
     Lill
    0.47
    افي
    0.47
    ুপ
    0.46
    Activations Density 0.000%

    No Known Activations