© 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. 11251
    Prev
    Next
    INDEX
    Explanations

    and she

    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
     also
    -2.03
    なども
    -1.73
     également
    -1.61
     również
    -1.57
     Якщо
    -1.54
    ſer
    -1.48
     також
    -1.47
     tiež
    -1.46
    もう少し
    -1.46
     enchufe
    -1.45
    POSITIVE LOGITS
     '',
    1.52
     '').
    1.49
     _('
    1.43
     Porque
    1.35
     plötzlich
    1.34
     การ
    1.33
     fluide
    1.32
    เพราะ
    1.29
    KURZBESCHREIBUNG
    1.27
    Ų
    1.27
    Activations Density 0.027%

    No Known Activations