© 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. 99542
    Prev
    Next
    INDEX
    Explanations

    Q: Now local

    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
     Periode
    -1.76
     kompatibel
    -1.52
    familien
    -1.50
     számára
    -1.45
    depan
    -1.42
    klä
    -1.41
    rrrr
    -1.38
    ᱓
    -1.37
    lohn
    -1.37
    wendige
    -1.35
    POSITIVE LOGITS
     is
    1.70
    J
    1.59
     that
    1.58
    >
    
    1.54
    D
    1.52
     five
    1.45
    M
    1.45
    U
    1.42
    ….
    1.41
    3
    1.39
    Activations Density 0.000%

    No Known Activations