© 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. 34-GEMMASCOPE-RES-131K
    7. 62625
    Prev
    Next
    INDEX
    Explanations

    contract termination and mutual consent

    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
    Negative Logits
    __':
    -0.88
    Transpose
    -0.78
    нном
    -0.78
     nazy
    -0.77
    férence
    -0.76
    umenter
    -0.73
    ⇧
    -0.73
     attesa
    -0.72
    Overlay
    -0.72
    ksjon
    -0.71
    POSITIVE LOGITS
     termination
    3.42
     terminate
    3.42
     terminated
    3.14
     terminating
    2.97
     Termination
    2.94
     terminates
    2.88
    Termination
    2.73
    termination
    2.64
    terminate
    2.45
    Terminate
    2.31
    Activations Density 0.023%

    No Known Activations