© 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. 12106
    Prev
    Next
    INDEX
    Explanations

    something or nothing

    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
    yled
    -1.88
    未満
    -1.72
    i
    -1.65
     Россию
    -1.63
     that
    -1.61
    vább
    -1.55
    ༀ
    -1.53
     Anſ
    -1.52
    事儿
    -1.52
    
    -1.52
    POSITIVE LOGITS
     gick
    1.52
    会う
    1.51
     you
    1.45
    CÓMO
    1.44
    úncia
    1.40
    ganz
    1.38
    SÍ
    1.37
     will
    1.34
    dä
    1.33
    Endereço
    1.32
    Activations Density 0.001%

    No Known Activations