© 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. 42249
    Prev
    Next
    INDEX
    Explanations

    only partly, partially, some, fraction, half

    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
     either
    -1.52
    Either
    -1.46
     just
    -1.46
     também
    -1.45
     hanya
    -1.41
     también
    -1.41
     sadece
    -1.38
     նաև
    -1.31
     pretty
    -1.30
     uniquement
    -1.30
    POSITIVE LOGITS
     will
    1.69
     включая
    1.33
    The
    1.31
    0
    1.24
    </em>
    1.23
    驟
    1.20
     it
    1.16
    amp
    1.16
     available
    1.14
     gdyż
    1.14
    Activations Density 0.077%

    No Known Activations