© 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. 84759
    Prev
    Next
    INDEX
    Explanations

    input field properties

    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
    jsp
    -0.77
     RPS
    -0.76
    textAppearance
    -0.75
    RPS
    -0.75
     бесе
    -0.74
    SMP
    -0.74
    Approve
    -0.74
     Bp
    -0.74
    totalPrice
    -0.73
    櫨
    -0.73
    POSITIVE LOGITS
     secure
    1.13
     auto
    1.05
    secure
    1.05
    underline
    0.98
     keyboard
    0.93
     secured
    0.92
    return
    0.88
     underline
    0.88
     editable
    0.87
     return
    0.85
    Activations Density 0.001%

    No Known Activations