© 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. 34-GEMMASCOPE-RES-131K
    7. 7021
    Prev
    Next
    INDEX
    Explanations

    Markov chains, probability distributions

    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
    င
    -0.74
     oscillatory
    -0.73
     pleural
    -0.73
     hef
    -0.71
     Verm
    -0.71
     Huey
    -0.69
    Anonym
    -0.69
    optarg
    -0.68
     regarded
    -0.68
     reflected
    -0.68
    POSITIVE LOGITS
     NICE
    0.96
     variational
    0.89
     log
    0.85
     로그
    0.82
    LOG
    0.82
    log
    0.80
    fattning
    0.78
    МІ
    0.78
     NHS
    0.77
     Arco
    0.77
    Activations Density 0.007%

    No Known Activations