© 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. 64906
    Prev
    Next
    INDEX
    Explanations

    COURT OF APPEAL licenses

    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
     Chol
    -0.75
    חד
    -0.72
     חד
    -0.72
    ริ
    -0.71
     spouse
    -0.71
    бота
    -0.70
     sinnvoll
    -0.69
    ashboard
    -0.69
    Joe
    -0.68
     esté
    -0.68
    POSITIVE LOGITS
    Pinch
    0.80
    anus
    0.73
    灘
    0.73
    Financi
    0.68
    
    0.67
     Pinch
    0.66
    eno
    0.66
     naselje
    0.64
     đeo
    0.63
     generated
    0.61
    Activations Density 0.045%

    No Known Activations