© 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. 12073
    Prev
    Next
    INDEX
    Explanations

    comments and remarks

    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
     Are
    -1.52
     учитывать
    -1.49
     be
    -1.48
     解
    -1.47
     ayude
    -1.45
     bande
    -1.41
    ल
    -1.41
    恒
    -1.39
    笛
    -1.38
    NÍ
    -1.37
    POSITIVE LOGITS
     about
    2.33
    5
    2.06
    7
    1.84
    8
    1.68
     czym
    1.58
    美味し
    1.50
    6
    1.48
     alemanes
    1.47
     españoles
    1.46
     zakoń
    1.43
    Activations Density 0.047%

    No Known Activations