© 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. 30927
    Prev
    Next
    INDEX
    Explanations

    continues or continuing

    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
    
    -0.90
    :?
    -0.87
    ENAS
    -0.86
    mercial
    -0.86
     exceedingly
    -0.85
    despite
    -0.85
     nadru
    -0.84
    duate
    -0.84
     réforme
    -0.84
     Надо
    -0.83
    POSITIVE LOGITS
     continued
    4.91
     continues
    3.89
     continue
    3.77
     continuing
    3.48
    continued
    3.47
     continuation
    3.41
    continue
    3.36
    Continued
    3.30
     Continued
    3.09
    继续
    3.00
    Activations Density 0.012%

    No Known Activations