© 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. 123823
    Prev
    Next
    INDEX
    Explanations

    these followed by noun

    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
    裃
    -1.77
     unſ
    -1.77
    龗
    -1.69
    今年も
    -1.66
    踅
    -1.63
     astronom
    -1.63
     goof
    -1.62
     unmistak
    -1.62
     glistening
    -1.61
     forbidding
    -1.59
    POSITIVE LOGITS
     and
    1.84
     as
    1.83
     when
    1.75
     which
    1.71
     on
    1.64
    俭
    1.59
     or
    1.59
     with
    1.55
     before
    1.53
     würd
    1.52
    Activations Density 0.014%

    No Known Activations