© 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. 66132
    Prev
    Next
    INDEX
    Explanations

    names and code elements

    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
     from
    -2.39
     how
    -2.06
     first
    -1.87
     you
    -1.71
     as
    -1.70
     by
    -1.66
     even
    -1.63
     so
    -1.62
     out
    -1.60
     what
    -1.60
    POSITIVE LOGITS
     CURRENT
    1.64
     caricatura
    1.57
    
    1.54
     grotte
    1.52
     STARTING
    1.52
     ส์
    1.50
     poë
    1.47
     ресто
    1.47
     distanciation
    1.46
    iosync
    1.46
    Activations Density 0.001%

    No Known Activations