© 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. 154516
    Prev
    Next
    INDEX
    Explanations

    legal or ethical conduct

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

    programming language constructs

    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
     こちら
    0.46
     entsprechenden
    0.46
    DVD
    0.45
     тесто
    0.44
     肩
    0.44
     carpeta
    0.44
     верх
    0.44
     本
    0.43
     ។
    0.43
     क्रमांक
    0.43
    POSITIVE LOGITS
    alty
    0.52
     juries
    0.52
     breakers
    0.52
     robbers
    0.49
     importers
    0.48
    লিন
    0.47
     grasslands
    0.47
     takers
    0.47
     studios
    0.47
     Domains
    0.46
    Activations Density 0.000%

    No Known Activations