© 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. 64703
    Prev
    Next
    INDEX
    Explanations

    Q David Jones

    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
    ܒ
    -0.78
    atau
    -0.77
     ivory
    -0.69
    φέ
    -0.69
     pruning
    -0.68
     میان
    -0.68
     globos
    -0.67
     Pruning
    -0.66
     flyg
    -0.66
     Twin
    -0.65
    POSITIVE LOGITS
     trecho
    0.78
    estu
    0.78
     firewall
    0.77
    ulha
    0.76
    secu
    0.75
    kema
    0.72
    θυ
    0.72
     hopping
    0.72
     security
    0.71
     encoder
    0.71
    Activations Density 0.010%

    No Known Activations