© 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. 1456
    Prev
    Next
    INDEX
    Explanations

    human language functions

    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
     With
    -2.27
    With
    -2.22
     with
    -2.22
     used
    -1.94
     new
    -1.94
     Also
    -1.93
    Also
    -1.80
     künf
    -1.80
    At
    -1.77
     any
    -1.76
    POSITIVE LOGITS
     berge
    1.60
     AMAZING
    1.58
     MICHAEL
    1.57
     lage
    1.55
     principes
    1.53
     semblent
    1.53
     incredi
    1.52
     lmao
    1.52
    oneof
    1.50
     composants
    1.49
    Activations Density 0.152%

    No Known Activations