© 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. 117183
    Prev
    Next
    INDEX
    Explanations

    sentence endings

    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
    ly
    -0.83
     Messiah
    -0.79
    月に
    -0.79
     ден
    -0.76
    czyk
    -0.75
    说完
    -0.75
     Soup
    -0.75
     Doe
    -0.74
    less
    -0.73
     рис
    -0.73
    POSITIVE LOGITS
     stopped
    1.37
     stops
    1.22
     stop
    1.13
     STOP
    1.11
    interrupted
    1.09
    STOP
    1.08
    stopped
    1.06
     interrupted
    1.05
    stops
    1.04
     cutoff
    1.02
    Activations Density 0.005%

    No Known Activations