© 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. 94800
    Prev
    Next
    INDEX
    Explanations

    positive descriptors and abilities

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

    common idioms and technical terms

    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
     κά
    0.52
     암
    0.52
     όπου
    0.52
     ყველა
    0.51
     كل
    0.50
     לצ
    0.49
     مشتر
    0.49
     ամ
    0.49
     δυνατό
    0.48
    ε
    0.48
    POSITIVE LOGITS
    नई
    0.47
    linestyle
    0.43
    nang
    0.42
    捋
    0.42
    kyat
    0.41
    滚动
    0.40
    人民
    0.40
    ,
    0.40
    keme
    0.40
     pasted
    0.39
    Activations Density 0.000%

    No Known Activations