© 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. 34279
    Prev
    Next
    INDEX
    Explanations

    instructions and actions

    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
     poë
    -1.54
     pakan
    -1.52
    がこの
    -1.51
     flotte
    -1.48
     kedi
    -1.42
     چنین
    -1.42
     aspek
    -1.41
    
    -1.40
    ebly
    -1.39
     inond
    -1.39
    POSITIVE LOGITS
     your
    2.88
     only
    1.73
     at
    1.67
     an
    1.65
     There
    1.62
     not
    1.60
     you
    1.59
     Some
    1.55
     from
    1.55
     overtly
    1.52
    Activations Density 0.011%

    No Known Activations