© 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. 1435
    Prev
    Next
    INDEX
    Explanations

    hex numbers and identifiers

    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
     with
    -1.96
     this
    -1.82
     these
    -1.49
     by
    -1.38
     all
    -1.34
     epitom
    -1.32
     their
    -1.31
     at
    -1.30
     in
    -1.24
     that
    -1.24
    POSITIVE LOGITS
    它
    1.51
    傒
    1.43
    了一些
    1.41
    Descriere
    1.41
    どうしよう
    1.41
     mélanger
    1.40
    确实是
    1.39
    SOME
    1.39
    也不知道
    1.38
     它
    1.37
    Activations Density 0.378%

    No Known Activations