© 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. 157250
    Prev
    Next
    INDEX
    Explanations

    designing or beautifying

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

    architectural and organizational 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
     канди
    0.44
     население
    0.44
    成功的
    0.41
    ELDS
    0.40
    कहां
    0.40
    Vista
    0.39
    교
    0.39
    Cand
    0.38
    Yeh
    0.38
    Candidates
    0.38
    POSITIVE LOGITS
     atrophy
    0.55
     Ayurvedic
    0.50
     ayurved
    0.49
     変
    0.49
     環境
    0.48
     transnational
    0.48
     INTERNAL
    0.47
    ブレーキ
    0.47
     abdominal
    0.46
     dialysis
    0.46
    Activations Density 0.001%

    No Known Activations