© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 28012
    Prev
    Next
    INDEX
    Explanations

    ordinal numbers and "old"

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

    sql code generation

    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
    还可以
    0.47
     yüzde
    0.46
    应当
    0.43
    没有
    0.42
    如果没有
    0.42
    陨
    0.40
    能够
    0.39
    储存
    0.39
    ,\
    0.38
     Honourable
    0.38
    POSITIVE LOGITS
     &
    0.73
     &/
    0.69
     ppl
    0.64
     Govt
    0.61
     compds
    0.58
     đc
    0.57
     yrs
    0.56
    govt
    0.55
     dgn
    0.54
     ਤੇ
    0.54
    Activations Density 0.098%

    No Known Activations