© 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. 70676
    Prev
    Next
    INDEX
    Explanations

    Paul, Minnesota

    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
    alamualaikum
    -0.91
     съм
    -0.91
     نیست
    -0.90
    𝐞
    -0.85
    чила
    -0.84
    atrices
    -0.82
    satunya
    -0.81
     като
    -0.81
     שלהם
    -0.81
    Alphabet
    -0.80
    POSITIVE LOGITS
    americas
    0.89
     especí
    0.89
     celebró
    0.88
     naszej
    0.85
     negó
    0.83
     Connectez
    0.82
     muertes
    0.82
    dico
    0.82
     Trouver
    0.82
     our
    0.81
    Activations Density 0.070%

    No Known Activations