© 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. 48091
    Prev
    Next
    INDEX
    Explanations

    surnames and numbers

    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
     historischen
    -1.35
    のサ
    -1.16
     besseren
    -1.13
     또
    -1.12
     einzigartigen
    -1.12
    ที่จะ
    -1.10
     only
    -1.10
     ところ
    -1.09
     wesentlichen
    -1.09
    --
    -1.08
    POSITIVE LOGITS
     pasaran
    1.12
    tiques
    1.10
    】:
    1.09
    ään
    1.07
    Ԁ
    1.06
     masakan
    1.05
    weiser
    1.04
    PageState
    1.03
     sisa
    1.03
    ές
    1.02
    Activations Density 0.154%

    No Known Activations