© 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. 28622
    Prev
    Next
    INDEX
    Explanations

    module.exports or require statements

    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
     its
    -1.24
     his
    -1.04
    FormUrlEncoded
    -1.00
     Befe
    -0.98
     even
    -0.98
    りたい
    -0.98
     already
    -0.95
     rs
    -0.95
     aż
    -0.95
     −
    -0.94
    POSITIVE LOGITS
    Oso
    1.13
    óri
    1.05
    Seni
    1.05
    Tils
    1.03
     tehdä
    1.03
     azonban
    1.01
    ները
    0.99
     そば
    0.95
    explained
    0.94
     estremamente
    0.94
    Activations Density 0.005%

    No Known Activations