© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 130841
    Prev
    Next
    INDEX
    Explanations

    end of the

    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
     proposent
    -1.86
    nearly
    -1.86
    typically
    -1.81
     eases
    -1.73
     unveils
    -1.73
     It
    -1.71
     MAKING
    -1.68
    ająca
    -1.68
    𖣔
    -1.66
     beaucoup
    -1.66
    POSITIVE LOGITS
     and
    2.42
     their
    2.25
     after
    2.13
     that
    1.98
     on
    1.96
     during
    1.94
     with
    1.91
     rigorous
    1.80
     despite
    1.80
     which
    1.77
    Activations Density 0.013%

    No Known Activations