© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 14128
    Prev
    Next
    INDEX
    Explanations

    external services, entrance menu, project add

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Эти
    -1.73
    修为
    -1.48
    Indien
    -1.44
    ﺶ
    -1.40
    Transk
    -1.40
    selbst
    -1.40
    behälter
    -1.38
     правительства
    -1.37
     Однако
    -1.32
     firſt
    -1.31
    POSITIVE LOGITS
    ﻷ
    2.06
    🪛
    2.00
    ﻹ
    1.84
     your
    1.80
    nitten
    1.64
    🩹
    1.48
    хів
    1.45
    ﺀ
    1.45
     quieres
    1.44
    ⬯
    1.42
    Activations Density 0.016%

    No Known Activations