© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 65203
    Prev
    Next
    INDEX
    Explanations

    community treatment message

    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
    桩
    -0.87
    asse
    -0.84
    [:]
    -0.79
     hires
    -0.77
    coeff
    -0.77
    kań
    -0.74
     いる
    -0.74
     Diagram
    -0.73
    cuento
    -0.73
    此时
    -0.73
    POSITIVE LOGITS
     message
    1.34
    Interaction
    1.14
     interaction
    1.13
     Interaction
    1.10
    message
    1.09
    interaction
    1.02
     Message
    1.00
    Message
    0.99
     Interactions
    0.95
     msg
    0.94
    Activations Density 0.015%

    No Known Activations