© 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. 105966
    Prev
    Next
    INDEX
    Explanations

    to introduce infinitives

    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
     will
    -2.34
     about
    -1.69
    pecabe
    -1.56
     also
    -1.55
     потому
    -1.48
     įva
    -1.45
     betyd
    -1.43
     comes
    -1.42
     well
    -1.41
     trö
    -1.34
    POSITIVE LOGITS
    such
    1.79
    Such
    1.55
     quinze
    1.46
     such
    1.41
     moderne
    1.41
     چنین
    1.40
     I
    1.39
     legendar
    1.38
     metic
    1.36
     solide
    1.34
    Activations Density 0.016%

    No Known Activations