© 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. 34-GEMMASCOPE-RES-131K
    7. 63438
    Prev
    Next
    INDEX
    Explanations

    future events or prior states

    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_34/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
     сначала
    -0.89
    nachweise
    -0.83
    гмента
    -0.79
    GridItem
    -0.79
     Hirsch
    -0.76
     όταν
    -0.75
    Şi
    -0.74
    XPATH
    -0.73
     понравился
    -0.72
     cewek
    -0.72
    POSITIVE LOGITS
     ahead
    7.28
    Ahead
    5.38
     Ahead
    5.31
    ahead
    4.94
     AHEAD
    4.09
     inför
    3.36
     prior
    2.63
     menjel
    2.52
     перед
    2.41
     before
    2.08
    Activations Density 0.164%

    No Known Activations