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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 22010
    Prev
    Next
    INDEX
    Explanations

    just followed by a 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
     только
    -1.63
     somente
    -1.61
     But
    -1.55
    präch
    -1.46
     intentó
    -1.39
     dúvidas
    -1.38
     estímulo
    -1.38
     vivió
    -1.38
     trataba
    -1.38
     ayudó
    -1.34
    POSITIVE LOGITS
     höhere
    1.49
    ccoli
    1.46
     they
    1.45
     notare
    1.41
     они
    1.38
     regista
    1.38
     höheren
    1.35
    '
    1.35
     memastikan
    1.33
    tenths
    1.32
    Activations Density 0.022%

    No Known Activations