© 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. 22-GEMMASCOPE-RES-131K
    7. 72708
    Prev
    Next
    INDEX
    Explanations

    code snippets and definitions

    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_22/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
     only
    -1.12
     unrelenting
    -1.12
    ilerini
    -1.09
     without
    -1.07
    Giới
    -1.07
     not
    -1.05
     time
    -1.00
    口气
    -0.99
    باح
    -0.98
     extraordinarily
    -0.96
    POSITIVE LOGITS
    ſſen
    1.40
     европей
    1.23
    摀
    1.21
    ᕮ
    1.21
    瘜
    1.20
    瓛
    1.20
     revered
    1.18
    GroupLayout
    1.15
    缑
    1.15
    傚
    1.14
    Activations Density 0.003%

    No Known Activations