© 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. 15166
    Prev
    Next
    INDEX
    Explanations

    numbers and locations

    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
     two
    -2.89
     three
    -2.36
     one
    -2.11
     δύο
    -1.63
    Two
    -1.63
     four
    -1.59
    สอง
    -1.52
     both
    -1.47
     Two
    -1.47
     people
    -1.41
    POSITIVE LOGITS
     cinquante
    1.52
     centaines
    1.48
     allerlei
    1.45
    ihnachts
    1.38
     dizaines
    1.35
     superbes
    1.34
     jouant
    1.31
     logiciels
    1.27
     nombreuses
    1.27
    hundreds
    1.27
    Activations Density 0.178%

    No Known Activations