© 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. 22-GEMMASCOPE-RES-131K
    4. 79724
    Prev
    Next
    INDEX
    Explanations

    namespace declarations

    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
     eventi
    -1.06
     élève
    -1.02
     coincid
    -1.01
    Verweise
    -1.01
    ಃ
    -1.00
     visites
    -0.99
     femininos
    -0.98
     prodej
    -0.98
     einzigartigen
    -0.98
     collecte
    -0.98
    POSITIVE LOGITS
     of
    1.11
    1.01
    }\
    0.99
     /
    0.98
     People
    0.97
    ;
    
    0.95
     not
    0.95
    ho
    0.90
     процен
    0.90
    }-\
    0.89
    Activations Density 0.007%

    No Known Activations