© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 16411
    Prev
    Next
    INDEX
    Explanations

    mimicking or simulating future 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_22/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
     Prato
    -0.96
     falda
    -0.95
     Wier
    -0.93
     bross
    -0.93
    measured
    -0.89
    volvement
    -0.88
     marka
    -0.86
     stund
    -0.86
     opin
    -0.85
    tried
    -0.85
    POSITIVE LOGITS
     future
    1.74
     real
    1.36
     later
    1.25
     späteren
    1.21
     zukünf
    1.21
     during
    1.20
     künf
    1.18
     similar
    1.15
     upcoming
    1.14
     przysz
    1.14
    Activations Density 0.228%

    No Known Activations