© 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. 22-GEMMASCOPE-RES-131K
    7. 33917
    Prev
    Next
    INDEX
    Explanations

    influence and creation

    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_22/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
    鏌
    -0.97
    ְּ
    -0.94
     lipids
    -0.94
    访问
    -0.91
    =");
    -0.88
    =")
    -0.86
    ELINES
    -0.86
    PutMapping
    -0.85
     nekaj
    -0.85
     Bous
    -0.84
    POSITIVE LOGITS
     our
    1.40
     design
    1.04
    現在の
    1.02
     shaped
    1.00
     create
    0.98
     new
    0.98
     develop
    0.95
    打造
    0.94
     shape
    0.89
    今回の
    0.89
    Activations Density 0.046%

    No Known Activations