© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 28278
    Prev
    Next
    INDEX
    Explanations

    .com domains

    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
    A
    -1.71
     That
    -1.60
     So
    -1.48
    L
    -1.45
     This
    -1.45
     Thus
    -1.43
    It
    -1.38
    P
    -1.38
     What
    -1.37
    D
    -1.37
    POSITIVE LOGITS
    Karakter
    1.52
    Absol
    1.51
     éven
    1.47
     extré
    1.38
    Spesifikasi
    1.38
    RemindMe
    1.38
     crédit
    1.35
    Awal
    1.34
     reager
    1.33
     geene
    1.31
    Activations Density 0.026%

    No Known Activations