© 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. 42049
    Prev
    Next
    INDEX
    Explanations

    programming code and structures

    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
     would
    -1.76
    tagHelper
    -1.56
    ?”
    -1.50
    incón
    -1.45
    TagHelpers
    -1.41
    ")==
    -1.37
     république
    -1.36
    ());
    -1.35
    ENCE
    -1.35
    enosis
    -1.34
    POSITIVE LOGITS
     the
    1.43
    umumkan
    1.40
     dejando
    1.38
    Suara
    1.38
    にほん
    1.38
    ༛
    1.37
     unor
    1.31
    おわりに
    1.28
    Seznam
    1.28
     アップ
    1.26
    Activations Density 0.007%

    No Known Activations