© 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. 41998
    Prev
    Next
    INDEX
    Explanations

    circular, oval, rectangular, round shapes

    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
     is
    -1.30
    PRESIDENT
    -1.21
    zości
    -1.19
     niv
    -1.17
     joc
    -1.16
    MIKE
    -1.15
     ley
    -1.14
    骤
    -1.12
     and
    -1.10
    tat
    -1.09
    POSITIVE LOGITS
    卧槽
    1.45
    lepší
    1.45
     dwindling
    1.41
    Shortly
    1.36
    𐐪
    1.33
    ſelves
    1.31
     createSprite
    1.30
    With
    1.30
     CascadeType
    1.30
     ungefär
    1.28
    Activations Density 0.197%

    No Known Activations