© 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. 68760
    Prev
    Next
    INDEX
    Explanations

    conditional distance

    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
    коны
    -1.00
     joão
    -0.99
    logitech
    -0.99
     leão
    -0.99
     acidente
    -0.96
     papai
    -0.96
     rios
    -0.96
     soto
    -0.94
    tiempo
    -0.92
     xadrez
    -0.91
    POSITIVE LOGITS
    missao
    0.91
    leq
    0.90
     от
    0.87
     initWith
    0.86
    esticular
    0.85
    нал
    0.84
     지
    0.83
    tilde
    0.82
    на
    0.81
    signable
    0.81
    Activations Density 0.019%

    No Known Activations