© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 28351
    Prev
    Next
    INDEX
    Explanations

    system calls and functions

    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
    んでる
    -1.34
    ˂
    -1.26
     molti
    -1.22
     ベージュ
    -1.22
     construit
    -1.21
     quadrado
    -1.20
     perpé
    -1.20
     awesome
    -1.20
    duled
    -1.20
     sarà
    -1.20
    POSITIVE LOGITS
     at
    2.08
     so
    1.70
     extraordinarily
    1.42
     after
    1.34
     kompetisi
    1.33
     can
    1.30
     supremely
    1.27
     what
    1.26
     if
    1.26
     one
    1.26
    Activations Density 0.089%

    No Known Activations