© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 129862
    Prev
    Next
    INDEX
    Explanations

    pad, pads, Padrino, footpad, padraic

    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
    .
    -2.95
    诹
    -2.55
    chiato
    -2.41
     —
    -2.36
    籏
    -2.33
    龊
    -2.30
    髕
    -2.28
    
    -2.25
    锜
    -2.25
     gemeins
    -2.23
    POSITIVE LOGITS
    In
    3.11
    可以
    2.72
    Because
    2.70
    Interestingly
    2.69
    Surprisingly
    2.67
    For
    2.64
    According
    2.64
    5
    2.56
    Historically
    2.56
     dasarnya
    2.55
    Activations Density 0.008%

    No Known Activations