© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 70518
    Prev
    Next
    INDEX
    Explanations

    rack and pinion railway

    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
     on
    -1.80
     most
    -1.45
    ↵↵
    -1.43
    理由は
    -1.38
     \
    
    -1.38
     Konkurrenz
    -1.34
     möglichen
    -1.31
    uscany
    -1.30
    Iné
    -1.30
    használ
    -1.29
    POSITIVE LOGITS
     a
    1.37
     ƙ
    1.35
     zoll
    1.34
    are
    1.29
    ah
    1.27
     davidson
    1.26
     eene
    1.24
     flèche
    1.21
    ang
    1.21
    amt
    1.20
    Activations Density 0.258%

    No Known Activations