© 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. 817
    Prev
    Next
    INDEX
    Explanations

    numbers like 24, 4, 1, 3

    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
     or
    -1.98
     first
    -1.75
     their
    -1.68
     if
    -1.67
     either
    -1.62
    hatian
    -1.60
    ⦑
    -1.45
     to
    -1.42
    deauna
    -1.38
     entregas
    -1.38
    POSITIVE LOGITS
    ’
    1.65
     ........
    1.32
    ...
    1.32
     scurt
    1.31
     motivi
    1.30
     of
    1.27
     capucha
    1.22
     propone
    1.21
    tion
    1.19
    ものは
    1.19
    Activations Density 0.100%

    No Known Activations