© 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. 75314
    Prev
    Next
    INDEX
    Explanations

    latex math and commands

    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
     just
    -2.31
     as
    -1.99
     undoubtedly
    -1.86
     or
    -1.84
     before
    -1.82
     because
    -1.77
     nestled
    -1.76
     in
    -1.73
     and
    -1.73
     When
    -1.71
    POSITIVE LOGITS
     of
    2.81
    ㈲
    1.95
     niedersachsen
    1.92
    部分が
    1.88
     rapidement
    1.87
    檍
    1.86
     centaines
    1.80
     the
    1.80
    羮
    1.80
     italiens
    1.80
    Activations Density 0.004%

    No Known Activations