© 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. 99667
    Prev
    Next
    INDEX
    Explanations

    search and index configuration

    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
    ='';
    -1.23
    (!__
    -1.23
     जहां
    -1.19
    랬
    -1.19
    わせる
    -1.19
     accesorios
    -1.18
    谥
    -1.18
    zieć
    -1.16
     Allí
    -1.16
    ឵
    -1.14
    POSITIVE LOGITS
     or
    1.20
     mahd
    1.15
    𝐱
    1.09
    ちなみに
    1.07
     niż
    0.99
    Crítica
    0.98
    หรือ
    0.97
     了
    0.97
     voulez
    0.96
    嫗
    0.95
    Activations Density 0.095%

    No Known Activations