© 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. 2632
    Prev
    Next
    INDEX
    Explanations

    Introduction sections

    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
     after
    -1.13
     so
    -0.97
     different
    -0.96
     what
    -0.95
     unique
    -0.91
     less
    -0.89
    十八
    -0.88
     had
    -0.87
     distinctly
    -0.87
     if
    -0.85
    POSITIVE LOGITS
    essentially
    0.94
     maniere
    0.92
     consom
    0.90
     .............
    0.90
    originally
    0.90
    massen
    0.89
     mech
    0.89
     ouvrage
    0.89
     ∆
    0.88
    umers
    0.87
    Activations Density 0.005%

    No Known Activations