© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 35446
    Prev
    Next
    INDEX
    Explanations

    programming return types (int, char, double)

    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
     "
    -1.11
     securing
    -0.99
    pectives
    -0.97
    struzione
    -0.97
     without
    -0.92
    Appellants
    -0.92
    ports
    -0.88
     provides
    -0.86
    برز
    -0.84
     outcrops
    -0.84
    POSITIVE LOGITS
     powodu
    1.19
     vélos
    1.13
    っぱい
    1.09
    れてる
    1.06
     ſmall
    1.05
    diğim
    1.03
    יוני
    1.01
     atlet
    1.00
    IKES
    0.99
     bezw
    0.98
    Activations Density 0.022%

    No Known Activations