© 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. 10-GEMMASCOPE-RES-131K
    7. 11846
    Prev
    Next
    INDEX
    Explanations

    numbers with 2

    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_10/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
     mohou
    -1.88
     môžete
    -1.80
     môže
    -1.71
    这个
    -1.67
    他的
    -1.66
     môžu
    -1.62
     může
    -1.61
     sostenibilidad
    -1.60
    sekten
    -1.55
    CARACTER
    -1.54
    POSITIVE LOGITS
     and
    1.70
     in
    1.63
    ."
    1.52
    ).
    1.38
     contando
    1.35
     wherein
    1.30
     within
    1.30
     overseen
    1.29
    มากๆ
    1.27
    S
    1.27
    Activations Density 0.316%

    No Known Activations