© 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. 29036
    Prev
    Next
    INDEX
    Explanations

    roads

    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
    boretum
    -3.14
    erintah
    -2.67
    伃
    -2.52
    髎
    -2.42
    缐
    -2.39
    垸
    -2.33
    u
    -2.30
    榀
    -2.28
    桢
    -2.27
    軚
    -2.27
    POSITIVE LOGITS
    -
    3.08
     roads
    2.50
    有
    2.48
    Zubereitung
    2.42
    可以
    2.38
    １
    2.34
    Leírás
    2.34
    Instead
    2.33
    AL
    2.33
    Roads
    2.31
    Activations Density 0.002%

    No Known Activations