© 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. 3764
    Prev
    Next
    INDEX
    Explanations

    clauses starting with that

    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
    even
    -2.02
     навіть
    -1.61
     EVEN
    -1.60
    Возраст
    -1.55
     kroppen
    -1.53
     حتی
    -1.52
     nawet
    -1.45
     наоборот
    -1.43
    噠
    -1.41
     XVI
    -1.40
    POSITIVE LOGITS
     there
    2.06
     one
    1.88
     when
    1.77
     we
    1.59
     they
    1.52
     possesso
    1.30
     after
    1.29
     was
    1.28
    (!__
    1.25
     includes
    1.24
    Activations Density 0.051%

    No Known Activations