© 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. 21912
    Prev
    Next
    INDEX
    Explanations

    fixed, version change, array

    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
     that
    -2.28
    "
    -2.28
     in
    -2.08
     with
    -2.08
     as
    -1.99
    </h3>
    -1.78
     for
    -1.77
     Also
    -1.74
    as
    -1.72
     of
    -1.68
    POSITIVE LOGITS
    ”),
    2.00
     zwanzig
    1.86
    妧
    1.84
     gier
    1.82
    σο
    1.77
     erwähnten
    1.77
    “:
    1.75
    uſe
    1.75
    ◨
    1.74
    ”).
    1.73
    Activations Density 0.004%

    No Known Activations