© 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. 21771
    Prev
    Next
    INDEX
    Explanations

    distance traveled or cover

    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
    
    -1.43
     outros
    -1.39
     キャプ
    -1.38
    鹮
    -1.34
     tornillos
    -1.34
     autres
    -1.32
     indiri
    -1.30
    毉
    -1.29
     materiał
    -1.29
    tably
    -1.29
    POSITIVE LOGITS
     traveled
    1.45
     Its
    1.41
    륜
    1.39
    chiha
    1.32
    ?
    1.31
    albeit
    1.30
     tingling
    1.28
     travelled
    1.28
     with
    1.26
     incul
    1.24
    Activations Density 0.040%

    No Known Activations