© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 175
    Prev
    Next
    INDEX
    Explanations

    conviction for murder or conspiracy

    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
     theyre
    -0.99
     oye
    -0.90
    ándome
    -0.90
    かれて
    -0.88
    landı
    -0.88
    uró
    -0.86
     abad
    -0.85
    chenta
    -0.85
    ⢄
    -0.84
    倀
    -0.84
    POSITIVE LOGITS
    But
    0.90
    We
    0.86
    !
    0.82
     Saint
    0.81
     our
    0.80
     estrictamente
    0.79
      
    0.77
     Ers
    0.76
    However
    0.76
     Sn
    0.76
    Activations Density 0.005%

    No Known Activations