© 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. 71184
    Prev
    Next
    INDEX
    Explanations

    mathematical functions and expressions

    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
     not
    -1.84
     constaté
    -1.58
     không
    -1.57
     retrouvé
    -1.55
     remarqué
    -1.47
     with
    -1.46
     véritables
    -1.43
    Não
    -1.40
     oublié
    -1.38
     Профиль
    -1.36
    POSITIVE LOGITS
     nor
    2.19
     anymore
    2.02
     yet
    1.80
    有任何
    1.68
     sondern
    1.64
     any
    1.53
     unless
    1.48
    yet
    1.41
    nor
    1.38
     its
    1.35
    Activations Density 0.183%

    No Known Activations