© 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. 22-GEMMASCOPE-RES-131K
    7. 36510
    Prev
    Next
    INDEX
    Explanations

    code and Bullfrog

    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_22/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
    
    -1.16
     kasus
    -1.01
     作り方
    -1.00
    Beskrivning
    -1.00
     ersten
    -0.94
    udz
    -0.91
    Haunted
    -0.90
    yfikacja
    -0.90
    irent
    -0.90
    yorum
    -0.90
    POSITIVE LOGITS
     again
    1.25
     dormitórios
    1.08
    czegó
    1.06
    ,
    1.00
    .
    0.97
    :</
    0.97
    нцип
    0.96
    0.91
     Tá
    0.91
    Perl
    0.90
    Activations Density 0.002%
    No Known Activations