© 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. 66417
    Prev
    Next
    INDEX
    Explanations

    to followed by verbs

    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
     δεν
    -1.62
     during
    -1.59
     prevents
    -1.55
     preventing
    -1.43
     ruptura
    -1.35
     embodies
    -1.34
    Zubereitung
    -1.34
     before
    -1.33
    –¿
    -1.32
     diinginkan
    -1.31
    POSITIVE LOGITS
    ’
    1.97
    8
    1.50
     be
    1.45
     see
    1.45
    This
    1.43
     эту
    1.41
     hear
    1.38
    が表示
    1.35
    再一次
    1.35
    為に
    1.34
    Activations Density 0.015%

    No Known Activations