© 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. 22-GEMMASCOPE-RES-131K
    7. 70578
    Prev
    Next
    INDEX
    Explanations

    ranks and lists

    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
     provide
    -1.12
     requesting
    -1.06
     until
    -1.03
     COMERC
    -1.01
     services
    -1.00
    多
    -0.99
     Kommentare
    -0.98
     two
    -0.98
    之前
    -0.97
     deliver
    -0.96
    POSITIVE LOGITS
    ということです
    1.30
    {?>
    1.20
    refreshing
    1.18
    ographia
    1.16
     []*
    1.16
     which
    1.16
    Recept
    1.14
    ፩
    1.13
    писок
    1.13
    tieth
    1.13
    Activations Density 0.030%

    No Known Activations