© 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. 10156
    Prev
    Next
    INDEX
    Explanations

    class of

    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
     E
    -1.20
     There
    -1.16
     відповід
    -1.10
     where
    -1.09
     According
    -1.07
    𝐙
    -1.07
    ưng
    -1.04
     on
    -1.03
     Honestly
    -1.02
    There
    -1.00
    POSITIVE LOGITS
    鹇
    1.45
    ographers
    1.40
    welli
    1.33
    衕
    1.32
    emore
    1.31
    ——”
    1.27
    (||
    1.26
    AreEqual
    1.26
    莚
    1.25
    ogenes
    1.24
    Activations Density 0.038%

    No Known Activations