© 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. 10-GEMMASCOPE-RES-131K
    7. 19548
    Prev
    Next
    INDEX
    Explanations

    then followed by a pronoun and verb

    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_10/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
     to
    -1.79
    ↵↵↵
    -1.62
     that
    -1.59
    en
    -1.59
     and
    -1.53
     nowadays
    -1.52
     this
    -1.52
     also
    -1.51
     such
    -1.49
     however
    -1.49
    POSITIVE LOGITS
     magia
    1.46
    もちろん
    1.45
     posible
    1.45
     prét
    1.41
     них
    1.39
    ńskich
    1.38
     vôtre
    1.37
     nôtre
    1.35
    特に
    1.34
     posibles
    1.33
    Activations Density 0.031%

    No Known Activations