© 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. 101503
    Prev
    Next
    INDEX
    Explanations

    long term durability

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

    common 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
    ي
    0.50
    i
    0.46
    其他
    0.44
    یو
    0.44
    俆
    0.43
    ür
    0.42
    残
    0.42
     boxes
    0.42
     resale
    0.42
     Containing
    0.41
    POSITIVE LOGITS
    та
    0.52
    чення
    0.51
     흐
    0.50
    ější
    0.49
     Krzy
    0.49
     ปลา
    0.49
     ดิ
    0.48
     १०
    0.48
     серь
    0.48
    Richt
    0.47
    Activations Density 0.000%

    No Known Activations