© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 127464
    Prev
    Next
    INDEX
    Explanations

    present invention

    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_10/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
    蟥
    -3.14
    z
    -3.13
    鲞
    -3.08
    <
    -3.06
    2
    -3.03
     overarching
    -2.81
    </h1>
    -2.70
    -2.70
    item
    -2.69
     magnific
    -2.59
    POSITIVE LOGITS
     Surprisingly
    3.25
     Even
    3.17
     Really
    2.95
     Ironically
    2.89
     Basically
    2.89
     strangely
    2.89
     Somehow
    2.81
     undeniably
    2.81
     ,
    2.80
     oddly
    2.78
    Activations Density 0.071%

    No Known Activations