© 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. 34-GEMMASCOPE-RES-131K
    4. 25595
    Prev
    Next
    INDEX
    Explanations

    patent application filing details

    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_34/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
     急
    -0.83
     Direkt
    -0.73
    бою
    -0.71
    因此
    -0.67
     reise
    -0.67
    tingly
    -0.67
     Marse
    -0.66
     waaronder
    -0.66
     or
    -0.66
     offent
    -0.65
    POSITIVE LOGITS
    Registro
    0.91
     utiliz
    0.83
    涝
    0.82
     walks
    0.81
    譎
    0.81
     Wirken
    0.80
    飆
    0.80
     PSI
    0.79
     Gland
    0.78
    erol
    0.78
    Activations Density 0.002%

    No Known Activations