© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 57173
    Prev
    Next
    INDEX
    Explanations

    court cases and legal documents

    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
    setOnItem
    -0.71
    modular
    -0.69
    ির
    -0.66
     δημο
    -0.62
     Modena
    -0.60
     reported
    -0.60
    ازات
    -0.60
     variants
    -0.60
     przeci
    -0.60
    lika
    -0.60
    POSITIVE LOGITS
     conformation
    0.86
     WoW
    0.74
     Gateway
    0.74
    CONTROL
    0.71
    zaw
    0.68
     gum
    0.68
    illot
    0.68
    Gateway
    0.66
     dirty
    0.66
    vature
    0.65
    Activations Density 0.071%

    No Known Activations