© 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. 71362
    Prev
    Next
    INDEX
    Explanations

    regularly and frequently

    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
     testSet
    -1.02
     cualquier
    -0.99
     CHORUS
    -0.96
     Hæ
    -0.94
    izarse
    -0.93
     direkten
    -0.93
    ;<
    -0.93
    enciales
    -0.92
     onCancelled
    -0.91
     campeón
    -0.90
    POSITIVE LOGITS
     your
    2.02
     or
    1.71
     you
    1.65
     yourself
    1.48
     like
    1.29
     regularly
    1.13
    Then
    1.12
    larınız
    1.12
     Then
    1.07
     frequently
    1.02
    Activations Density 0.034%

    No Known Activations