© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1130
    Prev
    Next
    INDEX
    Explanations

    words that match

    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_34/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
     Bolívar
    -0.85
    Balk
    -0.85
    PostConstruct
    -0.84
    readers
    -0.81
    itaries
    -0.79
    IENTS
    -0.78
    opies
    -0.77
     Duck
    -0.76
    SEAL
    -0.75
    Gail
    -0.75
    POSITIVE LOGITS
     match
    1.87
     matching
    1.83
     Matching
    1.55
     matched
    1.55
    match
    1.51
    matching
    1.51
    匹配
    1.46
    Match
    1.32
    Matching
    1.32
     matches
    1.31
    Activations Density 0.026%

    No Known Activations