© 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. 1314
    Prev
    Next
    INDEX
    Explanations

    request parameters and methods

    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
     each
    -1.46
     this
    -1.34
     their
    -1.31
     that
    -1.31
     when
    -1.27
     жил
    -1.20
    >
    -1.19
     For
    -1.12
     will
    -1.12
     =
    -1.12
    POSITIVE LOGITS
     celebrado
    1.28
    IBLES
    1.27
    рел
    1.25
     pomocí
    1.24
     différentes
    1.21
     klok
    1.20
    дизайн
    1.20
    战胜
    1.20
    "$_
    1.15
    cephala
    1.15
    Activations Density 0.036%

    No Known Activations