© 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. 127949
    Prev
    Next
    INDEX
    Explanations

    future time indicators

    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
     couvrir
    -1.79
     daer
    -1.73
     maintenir
    -1.67
     hunde
    -1.66
     preliminar
    -1.65
     zustand
    -1.61
     kopf
    -1.59
     ventes
    -1.59
     vider
    -1.58
     aussit
    -1.56
    POSITIVE LOGITS
     next
    2.03
     be
    2.02
     You
    1.96
     will
    1.84
     We
    1.81
     YOU
    1.79
     But
    1.77
     "
    1.76
     future
    1.73
     Those
    1.71
    Activations Density 0.091%

    No Known Activations