© 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. 10-GEMMASCOPE-RES-131K
    7. 44570
    Prev
    Next
    INDEX
    Explanations

    line of products or groups

    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
     if
    -2.17
     on
    -2.11
     noteworthy
    -2.08
     sizable
    -1.93
     There
    -1.88
     notable
    -1.87
     sizeable
    -1.85
     Even
    -1.84
     with
    -1.82
     Perhaps
    -1.82
    POSITIVE LOGITS
     famoso
    1.93
     !!!!
    1.92
     amazingly
    1.88
    
    1.88
     dando
    1.83
     dismal
    1.81
     sooo
    1.80
     strikingly
    1.78
     soooo
    1.77
     creat
    1.77
    Activations Density 0.020%

    No Known Activations