© 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. 58068
    Prev
    Next
    INDEX
    Explanations

    Unity YAML tag !u!

    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
     even
    -1.16
     before
    -1.06
     more
    -1.00
     all
    -0.99
     most
    -0.95
     despite
    -0.94
     one
    -0.94
     because
    -0.94
     with
    -0.93
     by
    -0.93
    POSITIVE LOGITS
    ఝ
    0.85
     REALLY
    0.85
     oscillation
    0.84
     DRAM
    0.84
     tenir
    0.82
     ELEMENT
    0.82
     ICP
    0.81
     SECOND
    0.81
     Drayton
    0.81
     NOV
    0.80
    Activations Density 0.001%

    No Known Activations