© 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. 2852
    Prev
    Next
    INDEX
    Explanations

    country affiliations

    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
    ใด
    -1.04
    ってない
    -0.99
    してない
    -0.97
     this
    -0.94
    していない
    -0.88
     following
    -0.88
    完成后
    -0.87
     bepaalde
    -0.87
     it
    -0.86
    してしまった
    -0.85
    POSITIVE LOGITS
     Correspondence
    1.16
    currently
    1.16
    現在
    1.10
    Emails
    1.10
     currently
    1.09
    现在
    1.09
     email
    1.08
    Correspondence
    1.03
    ғы
    1.02
    Corresponding
    1.00
    Activations Density 0.040%

    No Known Activations