© 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. 129054
    Prev
    Next
    INDEX
    Explanations

    on pace to soon

    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
     was
    -0.94
     وكانت
    -0.92
     была
    -0.90
     inmediatamente
    -0.89
    と思いました
    -0.87
     často
    -0.85
    してくれます
    -0.83
    ByteString
    -0.82
    wiada
    -0.82
     souvent
    -0.82
    POSITIVE LOGITS
     will
    1.79
     if
    1.37
     unless
    1.19
     this
    1.14
     gonna
    1.13
    bably
    1.09
     soon
    1.06
    gonna
    1.01
     tomorrow
    1.00
     due
    0.98
    Activations Density 0.037%

    No Known Activations