© 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. 70384
    Prev
    Next
    INDEX
    Explanations

    given condition or problem

    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
    ᡴ
    -1.42
    𐐀
    -1.30
    裥
    -1.27
    ὑ
    -1.26
    鮰
    -1.24
    ématique
    -1.23
    -1.20
     pensamos
    -1.18
    ées
    -1.18
    ी
    -1.17
    POSITIVE LOGITS
     menyebutkan
    1.57
     bahawa
    1.45
    一定会
    1.44
     bahwa
    1.43
    咙
    1.39
     alguno
    1.38
     there
    1.38
    りました
    1.37
    運び
    1.37
     menyebut
    1.36
    Activations Density 0.047%

    No Known Activations