© 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. 19743
    Prev
    Next
    INDEX
    Explanations

    manifold geometry

    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
    in
    -1.62
    ul
    -1.52
    ata
    -1.45
    ya
    -1.44
    us
    -1.44
    pre
    -1.40
    is
    -1.37
    ou
    -1.34
    ats
    -1.34
    if
    -1.32
    POSITIVE LOGITS
    seamnă
    1.51
     speranza
    1.45
    ப்பட்ட
    1.39
    Niveau
    1.37
     every
    1.37
     sorprendente
    1.36
    piscina
    1.34
     coscienza
    1.33
    Salir
    1.32
     casó
    1.30
    Activations Density 0.053%

    No Known Activations