© 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. 26096
    Prev
    Next
    INDEX
    Explanations

    administration and numbers

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

    observing changes and conditions

    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
     rozwoju
    0.49
    Ảnh
    0.48
    ษ
    0.48
    สำหรับ
    0.48
    FIND
    0.47
    Сегодня
    0.47
    罨
    0.47
     меня
    0.46
    垕
    0.46
    鍱
    0.46
    POSITIVE LOGITS
     grated
    0.45
     svm
    0.44
     streptomycin
    0.43
     suspicious
    0.43
     discretized
    0.42
     doubtful
    0.41
     hydrophilic
    0.41
     adipose
    0.41
     trembled
    0.41
     Minkowski
    0.41
    Activations Density 0.001%

    No Known Activations