© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 42829
    Prev
    Next
    INDEX
    Explanations

    suggesting an alternative

    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
    iksa
    -1.32
     không
    -1.22
     whom
    -1.21
    不出
    -1.20
     neither
    -1.18
     however
    -1.18
     französ
    -1.17
     岛
    -1.13
     չ
    -1.13
     enough
    -1.09
    POSITIVE LOGITS
     Instead
    1.84
     вместо
    1.53
    Instead
    1.48
     instead
    1.42
     malah
    1.35
    代わりに
    1.33
     vielmehr
    1.24
    内置
    1.23
    而是
    1.22
     use
    1.21
    Activations Density 0.025%

    No Known Activations