© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 74550
    Prev
    Next
    INDEX
    Explanations

    the phrase "like"

    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
     "
    -1.90
     and
    -1.84
     stycznia
    -1.68
     a
    -1.66
     grudnia
    -1.64
     ....
    -1.62
     as
    -1.60
     .....
    -1.56
    -"
    -1.54
     sierpnia
    -1.53
    POSITIVE LOGITS
     leeren
    1.65
    sometimes
    1.62
     abhängig
    1.59
    6
    1.59
     vítimas
    1.55
     famed
    1.52
     vostre
    1.49
    said
    1.47
    before
    1.46
    骜
    1.46
    Activations Density 0.027%

    No Known Activations