© 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. 47576
    Prev
    Next
    INDEX
    Explanations

    parts of words following common prefixes

    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
     ήταν
    -1.45
    transpiration
    -1.43
     πρ
    -1.41
    ==""){
    -1.40
    miniature
    -1.37
    umenter
    -1.32
    ^(@
    -1.30
     or
    -1.30
     sinistro
    -1.30
    denim
    -1.30
    POSITIVE LOGITS
    .
    1.89
     
    1.56
    к
    1.41
    <i>
    1.37
    บาง
    1.33
    CA
    1.31
    waters
    1.31
    on
    1.31
     scoperta
    1.31
    ating
    1.30
    Activations Density 0.017%

    No Known Activations